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

Annotations only declare readOnlyHint=false; the description adds real behavioral context beyond that, disclosing the error code (wreck_busy), a concurrency/retry requirement, and a claim-ownership rule for stale tows. Missing detail on what state is left after release, but clearly above the annotation-only baseline.

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 core action, and the parenthetical caveats are useful. Slight redundancy between the opening clause and the first parenthetical restating 'without moving the wreck', but no wasted bulk.

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-param mutation tool with no output schema, the description covers error modes, retry timing, and ownership rules, which is sufficient for correct invocation. Only the post-release state is left unstated.

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?

Single parameter with 100% schema coverage, so the schema already documents session_id fully. The description adds no parameter-specific meaning, making the baseline 3 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?

States a specific verb (release) and resource (wreck tow), and the 'without moving the wreck' clause distinguishes it from the sibling tow_wreck. Sibling differentiation is implicit rather than by name, so not quite a 5.

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 actionable context: a stale tow cannot release another tower's claim, wreck_busy is returned during a wreck update, and to retry next tick. These are practical selection/retry conditions, though it never explicitly says when to prefer this over tow_wreck.

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