diff_crawl

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally. The description still adds real behavioral context beyond that: verdicts are 'Hash-based' and sourced from a SQLite history index, telling the agent how changes are detected and that results are deterministic. It does not mention result volume or truncation behavior, which keeps it out of 5 territory.

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 core operation before the comparison-window detail and the sibling pairing. The 'Hash-based verdicts from the SQLite history index' clause is slightly implementation-flavored but still earns its place by explaining result derivation.

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?

With no output schema, the description still tells the agent the shape of the result (added/removed/changed pages) and the pagination parameters are documented in the schema. The workflow dependency on crawl_site incremental plus get_freshness is stated, so an agent can invoke it correctly without further context.

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 four parameters (since, offset, max_results, site_key) are already self-documenting, establishing a baseline of 3. The description reinforces the tricky one ('since') by explaining it as the most recent crawl whose crawl_ended_at <= since, but repeats rather than extends the 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?

States a precise verb+resource pair ('Return added/removed/changed pages') plus the exact comparison window, so the agent knows this is a historical page-set diff rather than a search or a page read. It is clearly separable from siblings like search_docs and get_page.

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?

Explicitly names the alternative workflow: 'Pair with get_freshness: pass the last_crawl_ended_at value as since after running crawl_site with incremental set to true.' This tells the agent both the prerequisite step and the prerequisite tool, and excludes casual use by tying invocation to a completed incremental crawl.

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