Ops Find

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

No annotations exist, so the description carries the full burden. It does disclose useful behavior — results contain each op's first line and shelf, ranking differs by mode, matching is against live op descriptions so it is never stale, and it returns only first lines rather than full text. It omits tie-breaking, empty-result behavior, and limits.

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?

One dense paragraph with colon-chained clauses and parenthetical asides that is harder to scan than it needs to be, given three distinct modes. The closing guidance about how to phrase an op's description ('Reach for it when ...') is advice for tool authors, not for a caller, and does not earn its place here.

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 discovery tool with an output schema and four optional parameters, this covers all invocation modes plus what the results contain. What is missing — the meaning of 'shelf', what a 'first line' is, and behavior on a miss — is minor against the output schema.

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 0%, so the description must compensate, and it mostly does: it explains need, role, category and n, and it enumerates valid role values (song, voice, sound, dj, mc, stage, film, dev), which the schema does not. It never states n's default of 8 or the set of category values.

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: 'Find the op for what you need, by purpose, from each op's own description.' That distinguishes it from ordinary content tools, though the jargon ('op', 'shelf') is never defined and no sibling (guide, playbook, lexicon_find) is contrasted.

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?

Each mode is spelled out with its selection condition: need returns the n best ops, role returns role-first shelves, category returns one shelf, and no arguments returns the shelves and roles. The need+role combination order is even specified. It stops short of exclusions or naming a sibling to use instead.

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