Narya Search

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

With no annotations, the description carries the full burden and does meaningful work: it discloses what the index covers (names, signatures, the comment above each declaration, annotation files), the scoping behavior of file/line, the session-scoped hole behavior, and that exact-name matches are ranked first. It omits auth/rate-limit and result-ordering details, but for a read-only search this is solid disclosure.

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?

Purpose is front-loaded in the first clause, followed by query-format guidance, index coverage, and scoping rules in a logical order. Every sentence conveys a distinct, actionable fact with no padding.

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 seven-parameter, zero-annotation search tool, the description covers purpose, query grammar, index scope, and the file/session/hole modes, and an output schema exists so return values need not be explained. Only the limit parameter is left uncovered, a minor omission.

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 0%, so the description must compensate, and it does for six of seven parameters: query formats (natural words, identifier fragments, book labels, exact names), file/line importability scoping, session_id+hole semantics, and kind values (def, axiom, data, codata, record). The limit parameter (default 10) is never mentioned, leaving one gap.

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 opens with a specific verb+resource: 'Find declarations (lemmas, definitions, types) by name, words or meaning,' and adds that Narya has no native search, clarifying this is a synthetic search layer. It does not, however, differentiate itself from the sibling narya_lookup, which plausibly overlaps.

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 gives clear conditional guidance: 'With file (and optionally line), only declarations importable there are returned' and 'With session_id and hole, the constants in the hole's type are added.' This tells the agent which parameter combinations trigger which scope, but no explicit when-not or named alternative is offered.

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