extract_rules_from_transcript

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

With no annotations, the description carries the burden and does so well: it declares the access level ('analyze'), states that no proposal is created (no mutation side effect), and lists the returned fields plus an instruction_for_client. It stops short of describing error or size/rate behavior, but the safety profile is clear.

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?

Front-loads the return contract, then the crucial non-mutation caveat and the access level. Slightly repetitive in listing returns twice (prose and field list), but nothing is wasteful or confusing.

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?

An output schema exists, yet the description still summarizes the payload and adds the access level and the 'no proposal created' caveat, which the schema cannot convey. Nothing needed to call it 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 description coverage is 100% and both params are documented there (private tag stripping, project_id resolving scopes). The description adds little beyond restating those, so the baseline of 3 is appropriate.

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 (extract) and resource (candidate rules from a transcript) and enumerates exactly what it returns (clean text, scope chain, existing rules, template). It is clearly distinguishable from the sibling extract_lessons_from_transcript.

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?

Explicitly scopes the tool's job ('Does not itself create any proposal') and names the follow-up alternative ('call create_pending_proposal per candidate'), so the agent knows both when to use this and what to do next.

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