Search Agent Skills

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

Annotations already cover readOnly/idempotent/openWorld, so the description's job is added context — and it delivers: it discloses what each result contains (scripts, network use, credentials, license, author, source and canonical URLs) and warns that all skills are third-party and should be reviewed before installing. That trust/safety signal is real value beyond the annotations; only return-format/pagination detail is absent.

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 scope statement comes first, followed by search mechanics and then result payload, which is the right ordering for a search tool. It is dense but every sentence carries information; the catalog enumeration is long but earns its place by making the tool's scope unambiguous.

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 7 optional params, no required inputs and no output schema, the description does the necessary compensation by describing the result payload and the third-party caveat. Only minor omissions remain (no mention of paging via offset/limit or result ordering), which keeps it short of a 5.

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 already 100%, so the baseline is 3, but the description adds genuine semantics: it clarifies that the keyword query is matched against title, summary and category (not just any text) and that the filters cover category, format, platform and OS. That meaning is not in the schema descriptions, so a 4 is warranted.

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 Swarmnest catalog of Agent Skills') and enumerates the catalog's contents (SKILL.md skills, plugin bundles, Cursor rules, AGENTS.md templates, prompt packs) plus supported agents. Very clear what it does, though it never names the nearest sibling (search_directory / get_entry) to draw a boundary.

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 by the field list ('Keyword search ...; filter by category, format, platform or OS'), which tells an agent how the tool is driven. However, there is no explicit when-to-use vs. when-to-use-a-sibling guidance and no stated prerequisites, so the agent must infer the routing itself.

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