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

Annotations already establish that this is a non-read-only, non-idempotent mutation, and the description adds the key cost disclosure that an AI credit is consumed. It does not say what happens if the retry also fails or whether the application's status is reset, which would make the retry semantics fully transparent.

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 short sentences, with the qualifying precondition front-loaded ahead of the cost note. The second sentence ('It uses an AI credit once ranked') is slightly awkward in phrasing but carries real information and no padding.

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 retry action with annotations present and no output schema, the description covers the essential precondition and the credit cost. Only the post-retry outcome (success/failure state) is left unaddressed, a minor gap at this complexity level.

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?

There is a single parameter with 100% schema description coverage, including format and a pointer to list_applications as the source of the ID. The description adds nothing about the parameter, which is acceptable given the schema does the work, so the baseline 3 applies.

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 names a specific verb ('tries again to rank') and resource ('an application'), and adds the triggering precondition 'whose ranking failed (match status failed)'. That precondition distinguishes it from rank_waiting_applications or set_ai_ranking without naming them explicitly, though the sibling differentiation is implied rather than stated.

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 gives a clear when-to-use condition: only for applications whose ranking has already failed. It does not name the alternative tools (rank_waiting_applications, set_ai_ranking) or explicitly say when not to use this, so an agent must infer the exclusions from the failure precondition.

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