Renewable exclusive leases and semaphores for workers; downstream fencing enforcement required.
Scored across 5 tools
Each tool maps to a distinct action in a claim lifecycle: acquire, release, renew, status, and wait. There is no overlap—acquire vs. wait are clearly differentiated (take now vs. block until available), and status is read-only.
All five tools use the exact same claim_<verb> snake_case pattern with consistent verb choices. Predictable and easy to scan.
Five tools is a tight, well-scoped set for a claim/lock coordination server. Every tool earns its place in the acquire-hold-release lifecycle.
The core lifecycle (acquire, renew, release, status, wait) is fully covered, including a blocking primitive. Minor gaps: no way to list/inspect all outstanding claims or force-release/steal a stale claim held by a dead agent.
CLAIM acquire
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | ||
| agent_id | Yes | ||
| capacity | No | ||
| resource | Yes | ||
| request_id | No | ||
| ttl_seconds | Yes | ||
| process_session_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden and delivers nothing: it does not say that acquiring is a mutating/locking operation, whether it blocks, what happens on contention, how ttl_seconds affects the claim, or whether acquisition can fail. Two words cannot cover the behavioral profile of a locking primitive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two words are technically concise but this is under-specification, not conciseness. Nothing is front-loaded because nothing is said, and the phrase contains no information an agent can act on.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 7-parameter, no-annotation, no-output-schema locking tool, the description is completely inadequate. None of the required fields (resource, agent_id, ttl_seconds), the mode enum, or the claim lifecycle is explained anywhere the agent can see.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 7 parameters, and the description adds no meaning for any of them. Key semantics such as mode=exclusive vs semaphore, the role of capacity, and the purpose of request_id/process_session_id are left entirely undocumented in both the schema and the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"CLAIM acquire" merely restates the tool name with a near-synonym and never states what is being acquired or what the operation produces. It is a tautology rather than a description of a verb+resource action, and it does nothing to distinguish this tool from claim_release, claim_renew, claim_status or claim_wait.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no mention of the four sibling claim_* tools, and no indication of when a claim should be taken versus waited for or checked. An agent has no basis for choosing this tool over claim_wait or claim_status.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CLAIM release
| Name | Required | Description | Default |
|---|---|---|---|
| lease_id | Yes | ||
| request_id | No | ||
| process_session_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden and delivers nothing. It does not say whether releasing is idempotent, whether it can fail if the lease is not held, whether it is destructive, or what permissions are required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two words are technically brief, but this is under-specification rather than conciseness; there is no front-loaded statement of purpose or any structure to speak of.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A lease-lifecycle mutation tool with no annotations, no output schema, undocumented parameters, and four siblings it must be distinguished from. The description provides none of the information an agent needs to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Three parameters with 0% schema description coverage and an empty schema-level documentation. The description explains none of them — it does not clarify which uuid is required (lease_id) or what request_id and process_session_id do.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"CLAIM release" is essentially a restatement of the tool name claim_release, adding capitalization but no verb-object specificity. It does not distinguish this tool from its siblings (claim_acquire, claim_renew, claim_status, claim_wait) or state what a lease claim entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus the four sibling claim_* tools, nor on prerequisites, timing, or the relationship between acquire/renew/release. The agent must infer the entire lifecycle.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CLAIM renew
| Name | Required | Description | Default |
|---|---|---|---|
| lease_id | Yes | ||
| request_id | No | ||
| ttl_seconds | Yes | ||
| process_session_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing. It does not state that renewal extends an existing lease, what happens to the TTL cap (86400), whether renewal is idempotent, or what errors occur for an expired lease.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two words are trivially short but this is under-specification rather than conciseness; there is no front-loaded, meaningful content. Nothing useful survives the trim.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A four-parameter mutation-adjacent tool with no annotations, no output schema, and 0% schema coverage needs a description to explain intent, side effects, and inputs. "CLAIM renew" supplies none of this, leaving the agent unable to call it correctly or confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across four parameters. The description mentions no parameter at all, so required fields lease_id and ttl_seconds, plus request_id and process_session_id, are entirely undocumented beyond their names and formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"CLAIM renew" restates the tool name with a verb (renew) but names no resource beyond the ambiguous token "CLAIM". It gives no hint that this renews a lease, nor does it distinguish itself from siblings claim_acquire, claim_release, claim_status, or claim_wait.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use, when-not-to-use, or alternative guidance whatsoever. With four sibling claim_* tools, the agent is given nothing to decide between renewing, acquiring, releasing, checking status, or waiting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CLAIM status
| Name | Required | Description | Default |
|---|---|---|---|
| resource | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, yet it says nothing about read-only safety, authentication, rate limits, or return behavior. It provides only a two-word label.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short, but it is under-specified rather than concise. It lacks the structure needed to communicate the tool's operation or its input.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with no annotations and no output schema, the description is completely inadequate. It omits purpose, usage context, parameter semantics, and any behavioral details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single required parameter "resource" has 0% schema description coverage, and the description adds no meaning about what a resource is or what format it expects. An agent cannot infer how to supply this parameter correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"CLAIM status" simply restates the tool name and lacks a specific verb or resource scope, so it reads as a tautology. It does not distinguish this tool from siblings like claim_acquire or claim_release.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no indication of when to use this tool versus alternatives such as claim_wait or claim_renew. There is no context or exclusion guidance at all.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
CLAIM wait
| Name | Required | Description | Default |
|---|---|---|---|
| resource | Yes | ||
| timeout_seconds | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden and discloses nothing. It does not say whether the call blocks, whether it is idempotent, whether it mutates claim state, what happens when the timeout elapses, or whether authentication is required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The text is short but that brevity reflects under-specification rather than concision. There is no front-loaded purpose sentence to anchor it.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter tool with a required resource, a timeout, no annotations, and no output schema, two words of description leave the agent with essentially no basis for correct invocation or result interpretation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description explains neither parameter. The required "resource" identifier and the "timeout_seconds" cap of 20 seconds are only visible in the raw schema, with no semantic explanation (e.g., units, blocking behavior on expiry) added by the text.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"CLAIM wait" merely restates the tool name rather than stating what the tool does. An agent cannot tell from this text whether it blocks until a claim is available, polls, or reserves a claim for later. It is a tautology, not a purpose statement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance whatsoever on when to call this versus the four siblings (claim_acquire, claim_release, claim_renew, claim_status). The word "wait" hints at a blocking variant of acquire, but nothing states the selection condition or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
claim_acquireclaim_releaseclaim_renewclaim_statusclaim_waitCoordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
Usage metering, spend cap (reserve before pay), lease lock, semaphore, heartbeat for agents. Free tr
Shared task queue for humans and AI agents: leases, handoffs, approvals and signed receipts.
Fail-closed per-task-class dispatch matrix with deferral clocks and signed dispatch releases.
Add one secure layer between your agents and this server.
