List Redmine project files

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description doesn't need to repeat safety. It adds valuable context: the tool never downloads files, changes data, and describes auth failures (401/403/404) and response sanitization. However, it doesn't describe the output schema details (though an output schema exists) and the allowance of fields, but that's beyond annotations. It adds significant behavioral context beyond the hints, but could include more about rate limits or response size (minor).

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?

The description is a single dense paragraph that's front-loaded with the core action and resource, then lists constraints and behaviors. It's efficient, with no fluff, but could be structured with bullet points for readability. The information is all relevant, and the length is justified given the complexity of the behaviors described.

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?

This is a read-only, one-parameter tool with a rich output schema. The description covers the essential call details (no query string, response ordering, sanitization, links, auth permissions, error codes, and non-destructive nature). Given the output schema exists, the description doesn't need to detail return fields. It's complete for an agent to call correctly, with no obvious missing information.

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% with a detailed description of project_id (positive numeric ID or valid identifier). The description adds the nuance that the ID must be positive numeric or valid identifier, but the schema already says that. The description doesn't add much beyond the schema, so baseline 3 is appropriate. It could clarify what 'valid project identifier' means (e.g., the pattern in schema) but that's already in schema.

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 clearly states the specific action ('Read a project's files') and the resource (GET /projects/:project_id/files.json). It distinguishes itself from siblings by specifying it's for the configured Redmine API user and focuses on files, which is distinct from list_projects, get_issue, etc. The purpose is precise and actionable.

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?

The description provides clear context for when to use this tool: to read a project's files, and explicitly notes it doesn't support pagination, filters, or includes, guiding the agent to use plain requests. It doesn't explicitly name alternatives like 'use list_projects to find project IDs' or when not to use it, but the context is clear enough for a read tool. It lacks explicit 'when-not-to-use' but the endpoint specification is sufficient.

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