task_lock_description

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

Discloses an important behavioral consequence beyond annotations: while locked, task_update refuses to change the description, while everything else remains editable. It also surfaces the safety-policy boundary about unlocking only on human request, which is valuable for agent behavior. No contradiction with idempotentHint=true or destructiveHint=false.

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 tightly written sentences carry the full behavioral contract: what the tool does, why it exists, and when unlocking is permitted. No filler or redundancy.

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 simple two-parameter tool with no output schema, the description fully covers the operational effect, the guardrail rationale, and the unlock policy. The annotations already cover idempotence and non-destructiveness, so nothing essential 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 description coverage is 100%, and both id and locked are already well documented inline. The description does not add new meaning to the parameters beyond restating the lock/unlock concept, so the baseline of 3 is appropriate.

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?

Opens with a specific verb-resource pair: "Lock or unlock a task's description." It explains the practical effect (task_update refuses to change it) and distinguishes the tool from task_update, making its role in the task workflow unmistakable.

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?

Provides clear context for when locking is appropriate: "a guard against rewriting the spec when you meant to add a comment." It also gives an explicit rule for unlocking: only when a human asks, never to bypass the refusal. It does not name an alternative tool for adding comments, but the intent is clear.

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