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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without description help. The description adds content-level context about what each catalog holds (rates, typical credits, per-call costs), but says nothing about result shape, volume, or whether entries are static config versus live data.

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?

Two sentences, front-loaded with the purpose and then a compact per-kind breakdown; every clause carries information. The inline parenthetical list is dense and slightly run-on, but no wording is wasted.

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 zero-required-parameter, two-parameter read tool with no output schema and closed-world annotations, the description covers the 'kind' dimension well. It leaves the nested free-form 'params' object entirely to the schema's pointer to guide(), and gives no sense of return shape beyond 'as entries', which is a real gap for a tool whose output the agent will consume directly.

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% and the enum is described only as 'The catalog', so the description genuinely earns credit by expanding each enum value into what it contains ('tiers ... with their rates', 'credits ... what each paid call costs'). It adds nothing for the free-form nested 'params' object, but the schema already routes that to guide().

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 enumerates exactly what the tool returns across six named catalogs (tiers with rates, media_models with typical credits, media_kinds, reviews, exports, credits with per-call costs), which is far more specific than the bare name 'catalog'. It never names a sibling, so an agent cannot tell from the description alone how this differs from 'guide' or 'find', and the verb (list/return) is only implied by 'as entries'.

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?

There is no statement of when to call this versus alternatives such as guide (which the schema points to for params) or find/read. The agent must infer that this is a discovery/enumeration step, and nothing says when it should not be used or what to do with the entries afterwards.

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