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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the exact output shape per site ('name (category, commands): about'), the paging mode, and a pointer to the nextPage field for offsets. It stops short of describing result ordering or ranking guarantees.

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 tightly packed sentences: purpose and scope first, then the query/no-query behavior, then the call to action. No filler, and the most decision-relevant information (query vs paging) comes before the parenthetical output format.

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 compensates by spelling out the return line format, and annotations cover the read-only safety profile. The only gap is workflow hand-off — it implies but never states that the listed commands are meant to be executed via a companion tool.

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 75% with limit/query/offset already documented in-schema, so the 3 baseline applies. The description goes further by tying the modes together — query changes the meaning of the call and the default limit — and by covering the purpose of the otherwise-undescribed category enum ('filter with category').

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 and resource ('Search the catalogue of 135 real websites clify can call') and immediately scopes what lives in it (package registries, gov data, science, news, etc.). It is clearly distinguishable from execution-oriented siblings like clify_run, since it returns sites and their matching commands rather than running them.

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?

Explicitly covers the two usage modes: pass a keyword query for ranked matches, omit it to page the catalogue one line at a time. 'Start here' signals it is the entry point of the workflow, but it never names the follow-on tool (clify_run) or clify_help as alternatives.

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