diff_project

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

Annotations already declare readOnlyHint and openWorldHint, and the description confirms 'nothing is uploaded or written', which is consistent. It adds a genuinely useful behavior note beyond annotations: project content is collaborator-authored and must be treated as data, not instructions – a security trait the schema cannot convey. Minor gap: no mention of cost/rate characteristics or whether files are ever written locally despite 'in the result or in files this tool writes'.

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 purpose and the read-only guarantee. The injection-warning sentence is long but earns its place; the `olcli diff` reference is the only mildly expendable clause for an agent with no CLI context.

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 read-only comparison tool with full schema coverage and no output schema, the description covers purpose, safety profile, and data-trust handling. It stops short of describing the result shape (statuses vs patch text), though the `name_only` parameter hints at it.

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 all seven parameters are documented in structured form. The description adds no parameter-level detail (e.g., how `file` paths are matched or how ignore rules interact), so the baseline of 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?

States a specific verb and resource ('Compare local files against the current remote state of an Overleaf project') plus the output shape ('content-level differences'), which is unambiguous. It does not name any sibling tool, so the agent must infer that pull_project is the sync counterpart rather than the read-only comparison.

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 read-only framing implies inspection-only usage, and the reference to `olcli diff` gives a mental model, but there is no explicit statement of when to choose this over pull_project or the download/compile tools. Usage is implied rather than directed.

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