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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: gains are computed by rescoring the report as if every finding of the rule were fixed, and each entry carries one example finding. It does not say whether results are sorted descending or what happens when a project has no findings.

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?

One dense sentence plus a clarifying clause; the most useful information (what is ranked and why) comes first. Minor cost: the opening is a noun fragment with no verb, so the agent must read the title to confirm this is a retrieval operation rather than a description of data.

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?

With only three fully documented parameters and no output schema, the description usefully sketches the return shape (per-rule point gain for overall and category score, plus an example finding). Remaining gaps are ordering guarantees and empty-result behavior, which are minor for a read-only ranking tool.

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%, so the schema already documents project (id, owner/repo, owner/repo@branch), runId (defaults to latest successful analysis), and limit (default 20, max 50). The description adds nothing about parameters, 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 states a specific resource and operation: the rules ranked by how many points fixing their findings would recover, including per-category gain and an example finding. It is clear what the tool returns, though it never names a sibling (e.g. get_findings or get_scoring) to contrast against, so differentiation is left to inference from the title 'Rank fixes by score gain'.

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?

Usage is only implied: the framing of 'cost the project the most points' suggests prioritization work, but there is no explicit when-to-use statement, no exclusion ('use get_findings for raw lists'), and no mention of prerequisites such as needing a completed analysis run. An agent can guess the intent but is not routed.

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