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

Annotations already declare idempotent=true and destructive=false, and the description adds the two facts an agent most needs: that 'files' REPLACES matching paths rather than appending, and that stale versions yield a 409 conflict response. These are non-obvious behavioral traits not derivable from the annotation set.

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?

Three sentences, front-loaded with the mutable surface, then the highest-risk semantic (replace) and the concurrency contract. No filler or restatement of the name/title.

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 7-param mutation with a nested file object and no output schema, the description covers the two dangerous behaviors (overwrite and conflict). It leaves unstated whether omitted fields are left unchanged and what the response contains, minor gaps given the 100% schema coverage.

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; the description earns above that by clarifying replace semantics for 'files' (path → content map that overwrites) and the read-then-pass workflow for 'version', which the schema terse line only hints at. It adds nothing for 'settings' or 'is_public', which the schema already covers.

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 (update) and resource (project) and enumerates the mutable surface: name, description, files, settings, visibility. It does not name or route against the closest sibling, write_project_files, which also writes file content, so an agent must still infer the boundary.

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?

Gives concrete usage instruction for the version parameter: read it via get_project first, and expect a 409 on conflict. It stops short of exclusions or alternatives, giving no guidance on when to prefer write_project_files or update_project_knowledge over this tool.

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