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

Annotations already cover readOnly/idempotent/destructive/openWorld, so the bar is lower, yet the description adds substantial beyond-annotation context: empty map means unobserved (never zero), rounding caveat via users_rounded_in_range, irregular every-few-days competitor capture, and an explicit auth requirement. This is exactly the behavioral disclosure an agent needs before trusting the numbers.

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?

Front-loaded with what is returned and the listings/competitors split, then caveats, then auth. Every sentence carries load, though the cadence and join paragraphs are denser than strictly necessary and the login command could be trimmed.

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 carries the full burden of explaining return values, and it does so precisely (ISO-date-to-value maps, empty-map semantics, rounding flags). Combined with the auth, roster, and failure-mode notes, an agent has everything needed to call and interpret this tool correctly.

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 the schema already documents each parameter, but the description adds meaning beyond it: store and days filter both listings and competitors, competitors implies include_competitors, and unlisted pairs hard-fail. The join key guidance (store, external_id; name is a label) further disambiguates the nested pair objects.

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?

"Daily-or-sparser history of an extension's numbers: user count, rating and ratings count, each as a map of ISO date to value" names a specific verb, resource, and return shape. It also distinguishes the two data families ("listings" vs "competitors") that the sibling list_competitors feeds, so an agent can tell it apart from get_extension without opening a schema.

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 clear conditional routing: include_competitors for the whole roster, competitors to narrow and implies include_competitors, and warns that an unlisted pair fails the call. It also instructs how to compare a rival to listings (dates present in both). It stops short of an explicit "use X instead if..." exclusion against siblings, but the context is unambiguous.

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