Stage Takes

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

With no annotations, the description carries the full burden, and it discloses real behavior: newest-first ordering, transcript sourcing (own audio vs. source performance clips), truncated text in output, and that matches report the hit word and its timestamp. It does not state a default/truncation for the result set beyond a truncated field, and never mentions the limit cap, so not a 5.

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 and ordering are front-loaded, and the filter semantics follow in a compact block. The telegraphic 'Lines: id, person, ...' phrasing is efficient, though the parenthetical asides make it slightly run-on.

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?

The tool returns rich records (an output schema exists) and the description still spells out the line shape, so the agent can act on results. The main gap for a 5-param read tool with zero annotation coverage is the unexplained 'limit' parameter and lack of any result-size behavior.

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 document all five parameters. It fully explains query (AND semantics, fields searched, case-insensitivity, hits format), person, and kept, but 'limit' is never mentioned and 'scene' is only implied by the possessive phrase. Coverage is therefore partial against a 0% schema.

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 opening clause names the resource ('a scene's takes'), the ordering ('newest first'), and the payload ('what the person said... its label and notes'), so the agent knows exactly what comes back. It also names two related siblings (stage_take_note, stage_take_transcribe), but never contrasts itself with list-like siblings such as stage_scene_list.

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 concrete conditions for the filter parameters ('query= words that must all appear...', 'person= one person's takes', 'kept=True only the kept ones') and routes note-taking and transcription to stage_take_note / stage_take_transcribe. No explicit when-not-to-use guidance or exclusion relative to other listing tools, so short of a 5.

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