hierarchical-codex

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.1.0
Disambiguation5/5
Every tool targets a distinct resource and action. Task operations (allocate, claim, start, heartbeat, release, block, fail, cancel, supersede, set_effort, commit) each have clearly defined, non-overlapping purposes. Result handling is split into candidate submission, checking, and verification with explicit role separation. No two tools are easily confused.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern with snake_case (e.g., artifact_get, task_allocate, result_verify, budget_report). Even multi-word verbs like result_submit_candidate maintain the convention. The naming is predictable and scannable.
Tool Count4/5
With 22 tools, the server is on the higher end but remains well-scoped for its purpose. The domain is complex — task lifecycle, artifacts, results, budgets, and recovery — and each tool covers a distinct operation without redundant overlaps. The count feels justified rather than bloated.
Completeness5/5
The tool surface provides comprehensive coverage for a mission/task orchestration system: mission lifecycle (create/get/close), full task state machine (allocate through commit, including failure and supersession), artifact storage, result verification pipeline, budget reporting, and recovery snapshot. No obvious dead ends or missing critical operations.
Average 3.4/5 across 21 of 22 tools scored. Lowest: 2.1/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 1 commit in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
Add a LICENSE file by following GitHub's guide. Once GitHub recognizes the license, the system will automatically detect it within a few hours.
If the license does not appear after some time, you can manually trigger a new scan using the MCP server admin interface.
MCP servers without a LICENSE cannot be installed.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavior. It mentions retaining the lease and hints at heartbeats or release, but it does not explain side effects such as state changes, whether the blocking dependency is recorded in a persistent way, or any implications for the worker or task. This is insufficient for a tool that mutates task state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The text is extremely brief—two sentences with no fluff—which is positive for conciseness. However, the wording is cryptic and fails to convey essential information clearly. It reads more like a placeholder than a well-structured explanation, so it does not earn a high score despite its brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 6 required parameters, no annotations, and no output schema, this description is severely inadequate. It does not explain the meaning or purpose of the parameters, the expected response, or any prerequisites. This leaves an agent without enough context to safely or correctly invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not mention any of the six required parameters (taskId, workerId, leaseToken, expectedVersion, idempotencyKey, reason). The schema provides only basic types and constraints; the tool's description adds zero semantic meaning about how these parameters are used or their roles in the blocking action.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it 'Record a blocking dependency while retaining the lease,' which indicates a specific action distinct from releasing or failing a task. However, the phrase 'Continue heartbeats or release the task' is ambiguous, making it unclear whether the tool itself executes those actions or offers instructions. This muddies the primary purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is given on when to use this tool versus alternatives like task_release or task_fail. The mention of 'retaining the lease' implies a scenario where the lease must be kept, but there is no direct instruction about prerequisites or conditions that necessitate this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden for behavioral disclosure. It only says 'Approval produces verified, not committed,' which hints at the workflow but fails to disclose idempotency details, version conflict handling, or side effects. This is inadequate for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no waste. But each sentence is concise without being thorough. It is not overly long, but the brevity leaves out critical context. Front-loaded information is adequate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A relatively complex workflow with 7 parameters, no annotations, and no output schema. The description is too sparse to guide an agent on correct invocation. It lacks context on expected versions, idempotency, and reviewer assignment. It feels like a placeholder.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for all 7 parameters. It does not mention any parameters, so the meaning of `evidenceRefs`, `expectedVersion`, or `idempotencyKey` is not clarified. Baseline for zero coverage and 7 params should be lower than 3, but the schema itself has descriptive names and types. Still, the description adds no value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool applies a second evidence gate to a checked result, which is specific about the resource and action. However, it could be clearer about what 'verify' means in contrast to 'check' and 'commit' among sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The phrase 'second evidence gate' implies a sequential step after checking, but there is no mention of when not to use it or alternatives like result_check or task_commit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions reading an 'authoritative' version and a set of related entities before mutation, but it does not disclose auth requirements, mutability side effects, Didžiuliai: no annotations. Because low annotation coverage, full burden. It adds that there is a status (status-quo) but no detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no waste, with primary action 'Read ... task ... before mutating it' front-loaded. It gives a compact overview.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a single-parameter getter used before mutation in a workflow. But no output_schema, no annotation, no description of param details, absence of explicit sibling differentiation and mutation workflow context. Given many siblings and the mutation function, this is incomplete for a minimal contextual workload.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has one required parameter (taskId) with no description. There is 0% schema coverage, and the description does not explain parameter meanings, formats, or default behavior. No compensation in description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Read') and names the resource ('authoritative task version') but does not explicitly distinguish from sibling mutation tools. It lists several components (lease, inputs, budget status) before mutation, which adds scope clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or alternative guidance is given. The phrase 'before mutating it' implies a mutation workflow, but no alternatives or exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of explaining side effects. It only states the state change without detailing concurrency controls, error conditions, or what 'result producer' entails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the core purpose without unnecessary verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The minimal description fails to provide sufficient context about the task lifecycle, the role of lease tokens, expected versioning, or how this fits with sibling operations. The schema constraints are present but unexplained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema lists 5 parameters with constraints but no descriptions. The description does not explain the meaning or purpose of any parameter, leaving the agent to infer from names alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: moving a leased task to running and establishing a result producer. This is specific and distinguishes it from sibling tools like task_claim or task_allocate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide guidance on when to use this tool versus alternatives. It does not mention prerequisites, sequencing with other task lifecycle tools, or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description bears the full burden for behavioral disclosure. It mentions the parent-authority constraint, but fails to disclose consequences like version checks, idempotency implications, side effects on the failed task or replacement, reversibility, or expected result behavior. This is a significant transparency gap for a mutating audit/closure operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences and front-loaded with the action. Every clause adds useful meaning—the main purpose is stated immediately and the authority condition follows without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity—8 parameters, no annotations, no output schema, and a mutating operation—the description is far too terse. It leaves out preconditions (task state requirements, replacement viability), the meaning of versioning/idempotency fields, and what the tool returns or changes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 8 parameters with 0% description coverage, yet the description does little to explain them. It loosely maps 'failed task' and 'replacement' to taskId and replacementTaskId, and the parent-authority note hints at parentLeaseToken/expectedParentVersion, but actorId, reason, expectedVersion, and idempotencyKey remain unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the primary operation: linking a failed task to a viable sibling replacement for audit and closure. It distinguishes from sibling tools like task_fail or task_cancel by introducing the replacement concept, though 'sibling' is domain jargon and not fully elaborated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the context (a failed task with a replacement available) and states one specific precondition: child supersession requires direct-parent authority. However, it does not explicitly contrast this with alternatives such as task_fail, task_cancel, or task_release, nor does it provide when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only mentions a possible side effect (unlocking dependents). It omits crucial details like whether the commit is destructive, permission requirements, failure modes, or how idempotency and versioning work, leaving significant gaps for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action and condition, and contains no filler. Every word contributes essential information, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with four required parameters, no output schema, and no annotations, the description is far from complete. It explains the trigger but not the meaning of parameters, expected behavior, error states, or operational prerequisites, leaving an agent under-informed for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the description makes no reference to any of the four parameters (taskId, actorId, expectedVersion, idempotencyKey). The agent must rely solely on schema constraints, which lack semantic meaning (e.g., why expectedVersion is needed), so the description adds no parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Commit a verified task') and specifies a precondition ('after every direct child is terminal'), which distinguishes it from sibling tools like task_fail or task_cancel. It does not explicitly contrast with alternatives but is specific enough to convey its unique role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'after every direct child is terminal' provides explicit when-to-use context, and 'This may unlock dependent tasks' indicates a beneficial outcome. However, it does not state when not to use it or suggest alternatives, so it lacks exclusions but is clear on timing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It adds useful behavior details: atomicity, optimistic versioning, and the lease token requirement. Still, it omits failure modes (e.g., version mismatch, task already claimed) and lease lifecycle behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the action and packs in atomicity, versioning, and lease token guidance. Every word contributes meaning, with no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, plus five parameters and a complex sibling group, the description is too sparse. It lacks failure semantics, idempotency behavior, lease expiration details, and explicit guidance on how this tool relates to task_allocate, task_start, and task_commit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it does not explain any parameter directly. 'Optimistic versioning' only implicitly hints at expectedVersion, and 'lease token' loosely relates to leaseSeconds. taskId, workerId, and idempotencyKey semantics remain undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Atomically claim'), the resource ('a ready task'), and the mechanism ('optimistic versioning'). It conveys the core purpose distinctly from generic wording, though it does not explicitly differentiate itself from sibling tools like task_allocate or task_start.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'Atomically claim a ready task' implies this is the step before worker mutations, and the lease-token requirement gives downstream context. However, it does not state when to prefer this over sibling tools or mention exclusions such as tasks not in ready state.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses the return value (mission ID and authoritative budget version) and the durable nature of the record. However, it omits details about idempotency, permissions, or side effects, though the idempotencyKey parameter hints at retry behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one concise sentence that front-loads the core action and adds return value context. Every word earns its place with no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a create tool with seven parameters, a nested budget object, and no output schema, the description is too sparse. It does not explain what 'durable mission record' entails, how budget limits are enforced, or how the authoritative budget version is used. The return value clue is helpful but leaves major gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description does not mention any parameter. With seven parameters including a nested budget object, the description provides no semantic guidance beyond the raw schema field names, leaving the agent to guess about constraints like risk or successCriteria.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Create'), the resource ('durable mission record'), and the ordering context ('before spawning any Terra agents'). It differentiates from sibling tools like mission_get and mission_close by conveying it is the create operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'before spawning any Terra agents' provides clear timing context for when to use the tool. It does not explicitly name alternatives or exclusions, but the sibling list makes the create-vs-read/update distinction implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description uses 'Read' to convey a non-mutating operation and adds the authoritative note. However, it omits any details on authentication, rate limits, or error behavior, which a read operation might not require but could still be disclosed. It provides some context but misses potentially important traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff. The first provides the core functionality and the second adds a valuable authoritative note. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with no output schema and no annotations, the description covers the essential purpose and a bonus tip. However, it leaves out details like return format, potential errors, or how the authority might affect usage, but these may not be critical for this tool. It's adequate but not exhaustive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It hints at the includeDetails parameter by mentioning 'optionally its task, artifact, claim, and review state,' but does not explicitly map this to the schema's parameter name or clarify the default behavior. It adds some meaning beyond the bare schema but leaves room for ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Read a mission' which is a specific verb and resource, and clearly scopes to optionally include related task, artifact, claim, and review state. While it doesn't explicitly name sibling tools for differentiation, the scope is distinct enough to avoid confusion in most cases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The sentence 'Treat this result as authoritative over chat summaries' implies a key use case—when ground truth is needed—but does not explicitly state when not to use this tool or point to alternatives. This is implied usage guidance rather than explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It adds useful behavioral context: policy-checking, the spawn_agent ordering, the returned task_id, and the role-edge restriction. However, it omits side effects, policy-failure behavior, idempotency semantics, and prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main action, and contains no filler. Every clause adds a distinct fact: policy-checking, spawn_agent ordering, task_id usage, and the parent-child role-edge constraint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 19-parameter mutation with no annotations and no output schema, the description is too thin. It provides the workflow hook and one output field but does not explain policy rules, required parameters, or behavior on invalid input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 19 parameters, and the description names none of them. It only references the returned task_id, leaving required fields like missionId, objective, role, capabilityPack, and idempotencyKey completely unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Allocate'), names the resource ('policy-checked work package'), and situates the tool in the workflow ('before native spawn_agent'). It also distinguishes this from sibling lifecycle tools by mentioning the returned task_id and the parent-child role edge constraint.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly states when to use the tool ('before native spawn_agent') and how to use its result ('Put the returned task_id into the child's prompt'). It also gives a key constraint ('only direct parent-child role edges are accepted'), though it does not explicitly name alternative tools for other phases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry behavioral disclosure. It mentions the consequence of an expired lease (reclaimed by another worker), which is useful. However, it does not disclose that this operation modifies state, bumps version, or handles idempotency, leaving some behavioral aspects implicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences with no extraneous filler. Every word adds value, stating purpose and usage timing efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With six parameters, no annotations, and no output schema, the description is incomplete. It explains the core purpose but omits return values, error conditions, parameter semantics, and lifecycle details needed for correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description provides no parameter explanations. The tool has six parameters including leaseToken, expectedVersion, and idempotencyKey, but the description does not clarify their purpose or required formats, leaving the agent to guess.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool renews an active lease, using a specific verb (renew) and resource (active lease). This distinguishes it from sibling tools like task_release, task_fail, or task_block, which handle other lifecycle actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use during long tool calls to prevent lease expiry, which is a clear when-to-use context. It does not name alternatives or exclusion conditions, but the context is unambiguous for an experienced agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses the separation-of-duties rule, the non-claiming invocation pattern, and the state effect of rejection. It does not explain success behavior or idempotency, but the core behavioral traits are covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences, each adding value: action, constraint, outcome. No fluff, well front-loaded, and easily scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 7 parameters and state-changing behavior, but the description omits critical details like approval outcomes, idempotency semantics, expectedVersion usage, and the role of notes/evidence. It is not sufficient for an agent to fully predict the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With schema description coverage at 0%, the description must compensate, but it only indirectly references taskId (as 'review_target_task_id') and approved (via 'Rejection'). The remaining parameters (reviewerId, expectedVersion, notes, evidenceRefs, idempotencyKey) are not explained, failing to add meaningful semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Independently check a candidate') and provides a resource context. It distinguishes from submission tools by emphasizing an independent review, but it does not explicitly contrast with the sibling 'result_verify' tool, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a concrete usage scenario: 'Luna verifiers call this on review_target_task_id without claiming.' It also specifies the reviewer/producer separation constraint. It lacks an explicit 'use this instead of X' exclusion but otherwise offers actionable context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden. It discloses that content is 'bounded,' that the store is content-addressed, and that the tool returns artifact references rather than content. However, it does not explain idempotency behavior despite requiring an idempotencyKey, nor overwrite/dedup semantics or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three dense sentences, each earning its place: purpose, required fields, and a usage/return strategy. Front-loaded with the core action and zero filler. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is moderately complex (8 params, enum, nested metadata, no output schema, no annotations), yet the description leaves significant gaps: no return-reference format, no idempotency semantics, no parameter meaning beyond names, no size-bound detail. The missionId warning hints at a known pitfall but does not fill the completeness gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It merely lists the required field names (already visible in the schema's required array) and warns against missionId. It does not explain the meaning or proper values of encoding, kind, metadata, mimeType, or content. The only real added semantic value is the missionId exclusion.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource: 'Store bounded content in the content-addressed artifact store.' This clearly distinguishes it from the sibling artifact_get (retrieval) and other mission/task/result tools. The 'content-addressed' qualifier adds mechanism-level specificity beyond the title.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides actionable usage context: required fields are listed, 'Do not send missionId' is an explicit exclusion, and the guidance to 'Return artifact references instead of copying large content into agent messages' tells agents when this tool should be used (large content scenarios). Does not name a specific alternative tool, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that the tool enforces terminal-state and acceptance conditions, but does not explain what happens on precondition failure, the irreversible nature of closing, versioning semantics, or effect of idempotencyKey. Some transparency is provided, but significant gaps remain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no filler. The primary action is front-loaded, followed by a key condition and a requirement. Every word contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has five parameters, no output schema, and no annotations, yet the description only covers the mission-completion precondition and acceptance decision. It omits critical context such as optimistic locking via expectedVersion, idempotencyKey usage, actorId semantics, and what the response indicates on success or failure. The description is too sparse for a state-transition tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for parameter meaning. It only hints at acceptFailedTasks through 'explicit acceptance decision' and says nothing about missionId, actorId, expectedVersion, or idempotencyKey. This is insufficient for a 5-parameter tool with no schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly defines the operation as 'Complete a mission' on the mission resource, distinguishing it from mission_create and mission_get. The precondition 'only after every task is terminal' adds specificity without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit guidance on when to use the tool: only after every task is terminal, and that failed tasks require an explicit acceptance decision. However, it does not explicitly name alternative tools or exclusion scenarios beyond the stated precondition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses a prerequisite (parent's version and lease token) and the condition (children terminal), but does not explain what cancellation actually does (state change, reversibility, side effects) or mention permissions, idempotency, or failure behavior. It adds some value but leaves many behavioral aspects obscure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the core action, and contains zero filler. Every word contributes to understanding the precondition and the unique parameter requirement.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 7 parameters, no annotations, and no output schema, yet the description is only a single line of conditions. It omits essential context such as the meaning of expectedVersion, idempotencyKey, actorId, and reason, and does not explain the effect of cancellation on the task hierarchy. It is far from complete for a complex lifecycle operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It only hints at two parameters (expectedParentVersion and parentLeaseToken) via 'direct parent's version and lease token', but it does not explain the other five required parameters (taskId, actorId, expectedVersion, reason, idempotencyKey) or their roles. This is insufficient given the high parameter count and lack of schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Cancel') on a specific resource ('non-terminal task') with a clear precondition ('after its direct children are terminal'). It also mentions the unique requirement for parent's version and lease token, distinguishing it from sibling tools like task_fail or task_supersede.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool: only after direct children are terminal. However, it does not explicitly exclude cases (e.g., tasks with non-terminal children) or mention alternative tools, so it stops short of a full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility. It discloses the state transition ('to ready') and the need for a reason, but omits critical behavioral details like the invalidation of lease tokens, versioning implications, or idempotency guarantees. It adds some value but is not rich enough for a higher score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with purpose, and contains no redundant information. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 required parameters, no output schema, no annotations, 0% schema descriptions), this description is far too sparse. It omits concurrency control details, parameter semantics, and post-condition behavior, making it incomplete for an agent to use safely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It only explains the 'reason' parameter ('Include a concrete reason'), leaving taskId, workerId, leaseToken, expectedVersion, and idempotencyKey entirely unexplained. This is insufficient for an agent to correctly use the tool without additional assumptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Return a leased/running/blocked task to ready') and the specific condition ('when the current worker cannot continue'). This distinguishes it from sibling tools like task_fail or task_cancel, which have different state transitions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides a concrete trigger condition ('when the current worker cannot continue'), but does not explicitly mention alternatives or when not to use it. The context is clear, but lacks the 'when-not' guidance that would earn a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full disclosure burden, and it does add meaningful behavioral context: it reveals that only a bounded prefix is returned (not the whole artifact) and that reading is the intended behavior. However, it stays quiet on what happens at the bound (truncation vs. error), response format, or whether there's pagination.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is optimally sized at two short sentences with the action front-loaded. The first sentence states precisely the core functionality; the second provides essential operational guidance without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-by-ID operation with a flat parameter list and simple output schema, the description adequately covers the essentials. It clearly states the tool's purpose, the nature of the read (bounded prefix), and the strategic preference for its use. It could be enhanced by touching on error behavior or offset/pagination options, but these are not required for basic operability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no parameters documented in the description), so the description must compensate. The phrase 'bounded prefix' conceptually maps to maxBytes, giving that parameter implicit meaning, but the description doesn't explicitly explain any of the three parameters' nuances or tradeoffs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific action verb ('Read'), identifies the exact resource ('artifact'), and adds critical scoping flavors: 'bounded prefix' and 'by ID'. It clearly distinguishes itself from siblings like artifact_put and communicates that this operation performs a scoped, targeted read rather than a full load.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'Prefer targeted retrieval over loading full artifacts' implies when to use this tool—for bounded, targeted reads—but stops short of naming explicit alternatives or exclusions. The usage context is implied by this guidance, but no sibling tool is directly mentioned as an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the read-only nature via 'Read' and mentions the bounded audit-event page, which adds some behavioral context. However, it doesn't address error cases, permission requirements, or what happens if the mission doesn't exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded with the action ('Read durable mission state'). Every word earns its place, and there is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has three parameters, no annotations, and no output schema. The description gives useful context about when and why to use it, but it omits parameter semantics and return details. For a recovery-related tool, this is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description provides no parameter-specific info. The phrase 'bounded audit-event page' hints at eventLimit and afterSequence, but it doesn't explain their meaning or the role of missionId. With three parameters and no schema descriptions, the description fails to compensate for the lack of parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Read' and identifies the resource as 'durable mission state and a bounded audit-event page', which clearly distinguishes it from sibling tools like mission_get or task_get. It also specifies the recovery contexts (interruption, compaction, client restart), making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool: 'after interruption, compaction, or client restart'. This gives clear context for its intended usage, though it does not explicitly name alternatives or exclusions relative to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are completely absent, so the description must disclose behavior. It mentions 'Atomically add' and 'Hard limits are enforced', which are important behavioral traits. However, it does not specify what happens when hard limits are exceeded (e.g., error, partial addition) or whether there are side effects. The atomicity and limit enforcement are valuable but not complete behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one concise sentence that includes the essential action, resources, targets, and constraints. It is front-loaded with the primary action and efficient, though it could benefit from a note about idempotency, but that is a completeness issue.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, no annotations, no output schema, nested usage object), the description is insufficient. It does not explain the idempotencyKey, optimistic concurrency via version fields, what 'hard limits' means specifically, or how usage is aggregated. The tool appears to be a critical financial/usage tracking point, but the description leaves many behavioral aspects for the agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must add meaning. The description mentions 'token, cost, wall-time, and tool-call usage', which correspond to the 'usage' nested object fields. However, it does not explain the required parameters like missionId, actorId, expectedMissionVersion, idempotencyKey, or expectedTaskVersion. It also doesn't clarify the purpose of idempotencyKey or version fields, which are critical for correct use.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (atomically add) and specific resources (token, cost, wall-time, tool-call usage) to a mission and optionally a task. This distinguishes it from other tools like task_heartbeat or task_commit, which have different purposes. The atomicity hint and hard limits are also mentioned.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates this tool is used for reporting resource usage to a mission/task, but it does not explicitly state when to use it vs. alternatives. Given the context of mission/task management, it's implied that this is for periodic reporting or at the end of a task, but not explicit. There's no mention of when not to use it or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses key effects: 'closes the producer lease' and that a reviewer must check it. It also adds behavioral constraints on artifactRefs and usage. While it does not mention potential side effects like idempotency or reversibility, the disclosed behaviors are significant and non-obvious from the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loads the main verb, and conveys essential information without fluff. Every sentence adds value: purpose, lease effect, artifact constraint, and usage advice. It is concise yet dense.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 10 parameters, nested objects, no output schema, and no annotations, the description is incomplete. It explains the purpose and a couple of parameter constraints but omits critical context about parameters like claims, summary, expectedVersion, idempotencyKey, and what the tool returns. An agent would need additional documentation to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It only provides semantics for two parameters: artifactRefs (must belong to taskId) and usage (include when known). The other eight parameters (e.g., claims, summary, expectedVersion) receive no explanation, leaving the agent to rely solely on the schema. This is insufficient for a tool with 10 parameters and nested objects.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Submit a worker result as candidate only.' It differentiates from verification tools (result_check, result_verify) by emphasizing 'candidate only' and requiring a 'different reviewer' to check it. The verb and resource are specific, and the scope is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context on when to use: submitting a candidate result for review, not final. It also provides a concrete prerequisite: 'artifactRefs must belong to this taskId — call artifact_put on the same task first.' However, it does not explicitly mention alternatives or when NOT to use it, though 'candidate only' implies avoiding this for final verification.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the operation is a change (implying mutation), specifies preconditions ('ready and unleased'), a ceiling ('within its recorded maximum'), and an authorization requirement for child tasks. This adds value beyond the schema, though it omits details like idempotency handling or error behavior. No contradiction with annotations since none exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no filler, and the key action is front-loaded. Every word contributes meaning (e.g., 'ready and unleased', 'recorded maximum', 'direct-parent authority'). This is appropriately concise for the information it conveys.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This tool has 8 parameters, no output schema, and no annotations, so the description must provide substantial context. It covers only the main purpose and two constraints, but fails to explain critical aspects such as the meaning of 'unleased', the exact authority chain, the versioning requirements, and the expected behavior on failure. An agent with this sparse description would struggle to use the tool correctly without further inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it provides no parameter-level guidance. It does not even mention the 'reasoningEffort' parameter or clarify the meanings of 'taskId', 'expectedVersion', or 'idempotencyKey'. The schema itself lacks descriptions, leaving the agent to infer from parameter names and the enum values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb 'Change' and resource 'model reasoning effort', and adds scoping conditions ('while a task is ready and unleased, within its recorded maximum'). This clearly distinguishes it from sibling task tools like task_allocate or task_commit, which handle different aspects of task lifecycle.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear usage condition: the task must be ready and unleased, and child changes require direct-parent authority. It implies when to use this tool (when adjusting reasoning effort under these constraints) but does not explicitly mention alternatives or when not to use it, so it lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing side effects. It clearly states that this tool clears the lease and charges usage, and it explains the impact on future sibling allocations. It does not mention error handling or edge cases, but the core side effects are transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise, and to the point. It contains no redundancy or irrelevant information, making it an efficient and well-structured summary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description gives essential operation details but lacks broader context, such as prerequisites (e.g., must have an active lease), error scenarios, or how this fits into the overall task lifecycle. The mention of future sibling allocations provides some context, but it does not fully round out the operational picture.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides no explanation of any of the 6 parameters (taskId, workerId, leaseToken, expectedVersion, idempotencyKey, reason) or the nested usage object. Although parameter names are self-explanatory, the schema coverage is 0%, and the description does not compensate by clarifying their roles or relationships.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: recording a definitive worker failure, clearing its lease, and charging final usage. It also distinguishes this from other task actions by mentioning 'definitive' and the actual-usage accounting, which sets it apart from cancellation or release.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (for definitive worker failures) and contrasts it with the alternative of counting full reservation vs actual failed usage. However, it does not explicitly name alternative tools or provide a decision tree, so it falls short of a fully explicit usage guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![codex-on-rails MCP server](https://glama.ai/mcp/servers/IrisRainbowNeko/codex-on-rails/badges/card.svg)](https://glama.ai/mcp/servers/IrisRainbowNeko/codex-on-rails)

Score Badge

Copy to your README.md:

[![codex-on-rails MCP server](https://glama.ai/mcp/servers/IrisRainbowNeko/codex-on-rails/badges/score.svg)](https://glama.ai/mcp/servers/IrisRainbowNeko/codex-on-rails)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/IrisRainbowNeko/codex-on-rails'

If you have feedback or need assistance with the MCP directory API, please join our Discord server