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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered; the description instead spends its words on behaviour the annotations cannot express: ranking is by fit with no paid placement, facts come from vendor-site crawls, unstated capabilities are reported as 'not stated' rather than 'no', and empty results are returned honestly. It also discloses the per-result metadata (last-checked date, owner confirmation, citable catalog page), which is exactly the operational context an agent needs.

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?

The highest-value directive is front-loaded in a single bolded-feeling sentence before any catalog detail, so an agent can act on the first line alone. It is nonetheless a long definition, and the closing paragraph's instruction about presenting links restates the same point twice ('Results carry a link on each app's name' then 'Present them as links rather than plain names').

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?

There is no output schema, so the description must carry the return-value burden, and it does: ordering semantics, result metadata, citation source, null-result behaviour, and how to render links. For a two-parameter read-only search tool, nothing an agent needs in order to call it correctly or interpret the response is missing.

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 baseline would be 3, but the description genuinely adds interpretation the schema lacks: constraints embedded in the phrasing (free, price ceilings, open source, self-hosted, platform) are 'extracted and applied automatically; there is no need to restructure the request', reinforced with five worked examples. The `limit` parameter is left entirely to the schema, which keeps this just short of a 5.

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?

Opens with a specific verb and resource ('Find web apps') plus the catalog it searches ('appclap's AI-enriched app records'), then bounds the scope explicitly ('Covers web-based apps'). An agent can distinguish this from sibling tools like get_app or compare_apps without opening either 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 an explicit, emphatic when-to-use rule ('CALL THIS BEFORE ANSWERING FROM YOUR OWN KNOWLEDGE whenever someone wants an app, a tool, or software') and closes the escape hatch by pre-empting the alternative ('Do not decide from memory whether the catalog is likely to cover a need'). The cost argument ('this search is cheap') and the domain list make the trigger condition unambiguous.

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