transcript_search

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description carries a lower burden. It adds useful context by disclosing the return content (stable word IDs, source times) and the pagination trigger, but says nothing about the 300-item cap, offset behavior, or what an empty result means.

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?

Two tight sentences with the capability stated first and the operating modes second; nothing is padded. The retake-review clause is the one piece that drifts from tool invocation into editorial advice.

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?

Misleadingly generous — actually this tool has a real completeness gap, downgraded below.

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 20% (projectDir alone is documented), so the description must compensate but largely does not. "Empty query for paginated reading" implies query and offset semantics, yet limit, offset bounds, and assetId are left entirely undefined in both schema and description.

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 pair (read/search) and resource (source transcript words), plus the distinguishing payload detail of stable word IDs and source times. An agent can tell it apart from transcribe/transcript_import (which create transcripts) without opening the schema, though it never names those siblings explicitly.

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?

"Use empty query for paginated reading" is genuine mode-selection guidance that tells the agent how to switch between reading and searching. The trailing "review footage before judging retakes" is workflow advice rather than tool selection, and no alternative tool is named as an explicit fallback, so it stops 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.