resolve_find_media_clip

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

Annotations are absent, so the description carries the full burden. It discloses key behaviors: case-insensitive matching, substring-based search on both name and metadata, and scope across all bins. It also notes the return format. However, it does not mention that the operation is read-only (implied by 'find'), nor does it explain the effect of the 'limit' parameter or whether both name and metadata criteria are combined with AND/OR. The phrase 'and/or' is ambiguous, leaving behavioral expectations unclear for edge cases.

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 description is exactly two sentences with zero fluff. It front-loads the core action, then adds return-value context and a clear caveat. Every phrase contributes value: 'case-insensitive', 'substrings', 'across all bins', 'exact names, media IDs and folder paths', and 'Not visual search' are all purposeful. It is exemplary in brevity and information density.

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 annotations, no output schema, and 0% schema parameter coverage, the description must carry the entire burden. It provides the essential purpose, return information, and a key exclusion, but lacks explicit parameter documentation (especially limit) and does not address usage scenarios relative to other search tools. The ambiguous 'and/or' and lack of guidance on combining criteria make it incomplete for a tool with three optional parameters.

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. It implies that 'query' is for name and 'metadata' for metadata substrings, but does not explicitly map each parameter. It completely omits 'limit', which has a default of 50 and likely controls result count. The structure of the metadata object (keys/values) is not explained, leaving the agent to guess the expected format. This is insufficient given the absence of schema descriptions.

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 ('Find'), a concrete resource ('shots' / media clips), and precise matching semantics ('case-insensitive name and/or metadata substrings across all bins'). It also explicitly contrasts with visual search, distinguishing it from sibling resolve_find_shots_by_visual_description. The return values ('exact names, media IDs and folder paths') further clarify intent. This is a clear, purpose-driven description that leaves no doubt about what the tool does.

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?

The description gives a clear context: it searches across all bins, and explicitly excludes visual search ('Not visual search'). This is an effective when-not rule, but it does not name the alternative tool (resolve_find_shots_by_visual_description) or mention other relevant siblings like resolve_list_media or resolve_find_timeline_clip. The guidance is helpful but not exhaustive, lacking explicit recommendations for when to choose this over other search tools.

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