StateLode

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare this is a safe, closed read. The description adds behavior an agent could not infer: ungranted workspace ids are rejected, and the returned updatedAt is a mandatory optimistic-lock token for later task_mutate calls. That is exactly the cross-tool constraint that prevents failed writes.

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?

Three tightly packed sentences: what it returns first, then the workspace targeting rule, then the lock requirement. No filler and the most consequential constraint is not buried.

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?

There is no output schema, so the enumeration of returned fields carries real weight, and the optimistic-lock dependency is stated. For a two-parameter read tool, nothing an agent needs in order to call it correctly and reuse its result is missing.

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 coverage is 50%, with workspaceId documented in the schema and id undocumented. The description compensates by explaining when and why workspaceId is needed, though it partly restates the schema's own workspaceId text and never explicitly defines id as the task identifier.

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?

States a specific verb and resource ('Fetch one task in full') and immediately enumerates the returned fields, which distinguishes it from task_search (listing) and task_mutate (writing). An agent can tell what this tool is for and what it returns without opening a schema.

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?

Gives a clear usage rule for workspaceId ('pass workspaceId from statelode://workspace to target a non-default workspace') and a hard prerequisite for calling task_mutate afterwards. It does not explicitly route discovery-style needs to task_search, so 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations, which only declare readOnly=false, destructive=false, idempotent=false. It documents optimistic-lock contract (updatedAt/expectedVersion, STALE_WRITE/STALE_PROJECT_POLICY carrying fresh state), null-clears semantics (dependsOn [], dueAt null, worker/owner null), project auto-creation and projectCreated:true, project_workspace_collision with no-write guarantee, SQUAD_BOUNDARY with suggestedRequest, and that attribution comes from the bearer token. No claim conflicts with destructiveHint=false since clearing is disclosed as explicit null input.

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?

Front-loaded with the { action, payload, workspaceId } shape and a bulleted action table where every bullet earns its place. It is still very long, and the Responsibility guidance paragraph (Team lead/Contributor/Observer) plus the self-referential note that squads are 'repeated in the server instructions' dilute focus without adding invocation value.

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?

No output schema exists, yet the description supplies the return signal an agent needs: projectCreated, STALE_WRITE/STALE_PROJECT_POLICY error payloads, project_workspace_collision meaning, and suggestedRequest. For a 12-action, nested-payload mutation tool spanning tasks, sprints, policy and squad requests, little is missing.

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 coverage is only 67% and the payload is a freeform additionalProperties object with a single pointer back to the description, so the description carries the full burden — and it does, enumerating required vs optional payload fields for all twelve actions. It also disambiguates owner vs worker vs legacy assignee and constrains status to workflow keys or categories.

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?

A specific verb (

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?

Explicit per-action routing plus negative guidance: no project_create exists, no separate plan tool, task_search with requests:"incoming"|"outgoing" is named as the read counterpart for squad requests. Workspace precedence rules spell out exactly when to ask the human versus proceed, which is real when-to-use guidance rather than inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description details behavioral traits far beyond the minimal annotations, including response structure (e.g., 'delegation', 'projectPolicy'), error handling logic (unknown_project error), and multi-workspace OAuth requirements.

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 dense, but every sentence is highly intentional, addressing a specific operational or behavioral requirement. It is logically structured to guide complex tool usage.

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?

Given the high operational complexity, involving multi-workspace contexts, defined project policies, and explicit filtering rules, this description is exceptionally complete.

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?

Given the extremely low schema coverage (9%), the description provides crucial context for complex parameters like 'projectId' (error handling if missing) and 'status' (how it affects result scope), effectively compensating for the missing schema detail.

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?

The description clearly defines the purpose as a 'lightweight' search for tasks, setting it apart from the full body retrieval of task_get and the mutation function of task_mutate.

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?

It provides explicit hierarchy instructions ('Use this FIRST'), detailed rules for filtering (e.g., 'NO status' = 'active' only), and necessary operational constraints (e.g., 'Always pass projectId').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.