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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds non-obvious context: results are permission-scoped to what the user can read, and the source is the control-plane view live_specs_ext via PostgREST GET. It stops short of disclosing paging defaults, result caps, or ordering.

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 tight sentences, with the what/scope front-loaded before the optional filters and the backend reference. Every clause carries information, though the raw PostgREST endpoint/table notation is internals an agent rarely needs and is the one bit of low-yield text.

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 partly compensates by naming the returned payload ('connector + last-publication metadata') and the visibility scope. It still leaves the exact result shape, field set, and default/max limit behavior unspecified, which is a modest gap for a list endpoint.

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 limit, offset, spec_type, and name_prefix are fully documented in the schema (including the like wildcard behavior). The description's mention of prefix and spec_type filtering largely repeats that, adding no syntax or format detail beyond it. Baseline 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?

The description names a specific verb and resource ('List live catalog entities'), enumerates the entity kinds (captures, collections, materializations, tests), and adds the returned metadata (connector + last-publication). The word 'live' implicitly separates it from the draft-oriented siblings (list_drafts, list_draft_specs) without needing the 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?

It states the optional narrowing filters and the read-only visibility scope ('the user can read'), which implies the read path, but never names an alternative tool or states a when-not condition. An agent must infer that single-entity lookups belong to get_catalog_spec and count queries to get_catalog_stats.

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