Search within a transcript

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

Annotations confirm read-only and idempotent behavior; description adds that it returns timestamped segments and implies efficient partial retrieval. It does not contradict annotations but could further detail return format or pagination (e.g., max_results).

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?

Single sentence, front-loaded with key action and benefit. Every word serves a purpose, no extraneous information.

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?

Given 6 parameters and no output schema, description is too brief. It covers core function but omits parameter details and output structure. Adequate for basic understanding but incomplete for full agent autonomy.

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 only 17% (only context_segments described). Description only implies 'phrase' corresponds to the 'query' parameter. No explanation of job_id, whole_word, case_sensitive, or max_results, leaving agent unclear on how to configure search.

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?

Description clearly states it searches within a transcript for a phrase and returns matching timestamped segments. It distinguishes from siblings like 'get_transcription' (whole transcript) by specifying the focused search capability, and emphasizes use for long recordings.

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?

Description hints at when to use: 'without loading the whole transcript into context' suggests it's for targeted extraction. However, it does not explicitly state when not to use or list alternative tools like 'get_transcription', leaving some ambiguity.

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