get_edit_transcript

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

With no annotations, the description carries the full burden and does so: it discloses the required 'recordings:write' scope and why (it exposes text of cut words), the page-size cap, the pagination trigger, and the returned cut/revision state. This is far more behavioral context than annotations would typically provide.

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 the edit_recording relationship are front-loaded, and the paging and scope details follow in a logical order. Density is high but nearly every clause carries information, though the approximateWordTimings sentence reads as a slight non-sequitur.

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?

There is no output schema, so the description must explain returns — and it covers the word payload, indices, timeline basis, filler/removed flags, cuts, revision, and paging. Nothing an agent needs to call and consume this correctly is missing.

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 100%, so the baseline is 3, but the description adds operational meaning the schema lacks: fromWord is tied to the nextFromWord paging loop, and the page size is framed as up to 1,500. It does not clarify limit's behavior when transcripts are shorter than a page.

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+resource ('Read a recording') and immediately frames scope against the sibling it pairs with ('the way edit_recording edits it'). An agent can distinguish this from get_transcript and edit_recording without opening a schema.

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?

Gives concrete procedural rules: page when 'transcript.nextFromWord is not null' and call again with fromWord, and cut whole sentences when approximateWordTimings is true. It stops short of explicitly naming get_transcript as the plain-text alternative, so routing between the two transcript readers is left implicit.

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