ipa_find

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

With no annotations, the description carries the burden, and it does disclose useful traits: results are ranked candidates, ties are broken by the user's lab, and there is a cross-tool dependency on ipa_status. It does not state that the operation is read-only, whether it searches across all labs or only the current one, or what happens on zero matches.

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?

Roughly four short lines, front-loaded with the question the tool answers, then examples, then the tie-break rule and the escalation rule. Every element earns its place and nothing is repeated from structured fields.

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 one-parameter lookup with no output schema, the description covers what comes back (ranked candidates), how ranking is influenced, and how to resolve multi-lab ambiguity. The main residual gap is failure behavior when nothing matches, which an agent would need before calling.

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% on the single 'query' parameter, so the description must compensate, and it does with concrete example inputs ('the spinning disc', 'the Nikon scope', 'Dobby') that reveal the field takes loose natural-language descriptions rather than IDs or exact names. It stops short of specifying matching rules (substring vs fuzzy, aliases).

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 frames a specific job: resolving a vague user reference ('the spinning disc', 'Dobby') into ranked item candidates, which is a clear verb+resource in effect. It never names the sibling it is not (notably ipa_search and ipa_item), so an agent must infer whether to use this or the search tool.

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 real procedural guidance for the ambiguous case: consult ipa_status for the user's lab, use the lab to break ties, and ask the user rather than guessing when multiple labs match. However, there is no explicit statement of when to reach for ipa_find versus ipa_search/ipa_item, which is the primary routing decision an agent faces.

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