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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: where the items originate (a failed deployment or the repository check), that they are assigned to the person's coding agent, and that only *open* ones are returned — a filtering behavior the annotations do not express.

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 resource name, then one dense sentence carrying provenance, scope and the read-only guarantee, with zero filler. The parenthetical '(a failed deployment, or the repository check)' is slightly heavy but earns its place by explaining the data source.

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?

A two-optional-parameter, annotation-rich listing tool with no output schema; the description covers scope, provenance, filtering to open items, and side-effect status, which is enough to call it correctly. Minor gaps remain around ordering and volume of results, which an agent would otherwise want to know for a potentially unbounded 'every project' listing.

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 100%, so baseline is 3, but 'in every project or one' adds meaning the schema does not: omitting `project` means all projects rather than one. That is a genuine semantic clarification for an optional parameter. The `workspace` parameter is left to the schema, which documents it adequately.

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 ('Fix requests: problems in the person's code that stop a deploy ... Lists the open ones'), including provenance (The Deployer, failed deployment or repository check) and the assignment target (the coding agent). An agent can tell this apart from generic inspection tools, though it never explicitly names its near-identical siblings `fix`, `fix_status`, `claim_fix`, or `report_fix`.

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 implied rather than stated: 'Lists the open ones, in every project or one' tells the agent it is a read/listing call and that scoping is optional, and 'Changes nothing' signals it is not the tool for acting on a fix. There is no explicit when-to-use vs when-not guidance and none of the very similar sibling names are mentioned, so an agent must infer which of `fixes`/`fix`/`fix_status` to pick.

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