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

Annotations already declare readOnlyHint=true, and the description goes further by disclosing the returned metric set, the per-time-grain aggregation, and the optional timestamp bounding — valuable behavioral context given there is no output schema. It stops short of covering ordering or pagination behavior beyond the limit param.

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 compact sentences, front-loaded with what is returned before the optional filtering and provenance details. The PostgREST endpoint mention is marginally useful but is the one element that 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?

No output schema exists, but the description compensates by naming the returned fields, and annotations cover the read-only safety profile. Remaining gaps (row ordering, whether limit defaults, behavior with no matching rows) are minor for a read-only stats query.

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 grain, limit, ts_start/ts_end and catalog_name are already documented with formats and defaults. The description only restates that results are per time grain and optionally time-bounded, adding no syntax or edge-case detail beyond the schema — baseline 3 is appropriate.

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 (get) and resource (catalog stats) and enumerates the exact metrics returned — bytes/docs read/written, usage_seconds, errors, txn_count — so an agent can distinguish it from estuary_get_catalog_spec or estuary_list_catalog at a glance. Names the backing view and endpoint, reinforcing scope.

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?

Usage is implied rather than stated: it retrieves per-grain usage stats for one entity, optionally time-bounded. There is no explicit when-to-use/when-not guidance or routing to siblings (e.g., use get_catalog_spec for configuration), so an agent must infer the boundary itself.

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