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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses project-scoping behavior ('acts only on the explicit project_id', 'active-project pointer is never used to guess') and output characteristics (program time, source spans, repeated-phrase detection). This adds meaningful behavioral context beyond what annotations alone 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?

The description is compact and front-loaded with the key scoping constraint, and the usage rule is clearly stated at the end. The first sentence is slightly awkward and somewhat redundant with the second, but overall every part earns its place.

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, but the description does summarize what the result contains: the kept transcript, program time, matching source spans, and repeated-phrase detection. Combined with the one required parameter and read-only annotations, this is sufficient for an agent to invoke the tool and understand the purpose of the result.

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 100% and the project_id schema description is already detailed, including where to copy the id and that the active-project pointer is not used. The tool description mostly repeats the scoping concept without adding new parameter-level detail.

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 description states a specific resource ('the transcript the CURRENT edit actually keeps') and adds differentiating detail (program time, matching source spans, repeated-phrase detection). It is clear it returns the kept transcript rather than a general transcript, though the phrase 'returns the project identity with its result' is somewhat confusing.

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 an explicit when-to-use rule: 'ALWAYS call this after cutting repetitions or tightening — it is how you verify nothing repeated survived.' This is clear context for the intended use case, though it does not name alternatives or explicitly state when not to use it.

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