write_document

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

The description goes beyond the minimal destructiveHint annotation by revealing two important behaviors: the previous content is backed up locally before any replacement, and the write can be refused if expected_uuid doesn't match (optimistic concurrency). These are not disclosed in annotations or schema, so the description carries the burden and does so thoroughly.

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 three sentences, each serving a distinct purpose: core action, safety mechanism, and concurrency control. No wasted words, and the most important information is front-loaded.

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?

The tool has 5 parameters, no output schema, and a single annotation. The description explains the primary write/replace behavior, the backup guarantee, and concurrency protection, which covers the main risks and usage context. It does not describe return values or distinguish from batch tools like push_documents, but for a single-document write tool, the coverage is strong.

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?

With 0% schema description coverage, the description must explain parameters. It explicitly clarifies 'overwrite=true' for replacement and explains the purpose of 'expected_uuid' (from read_document) to prevent overwriting teammate changes. The remaining parameters (project_id, file_name, content) are left to inference from their names, but the non-obvious semantics are well covered.

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 verb and resource: 'Create a document, or replace one with overwrite=true.' This distinguishes it from siblings like read_document and delete_document by specifying creation and replacement behavior.

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: create a new document or replace an existing one, with overwrite=true for replacement. It also mentions using expected_uuid from read_document for concurrency checks, directly tying to a sibling. It does not explicitly state when not to use it, but the context is strongly implied.

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