extract_mentions

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

The description explicitly declares the tool is a 'Side-effect tool' and clarifies that writes happen only when confirm=true. With no annotations present, this is valuable behavioral disclosure beyond the tool name. It does not detail overwrite behavior or artifact location, but the key side-effect warning and confirmation requirement are clearly stated.

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 a single sentence with no filler, and the critical 'Side-effect tool' warning is front-loaded. It loses one point because it is so minimal that it sacrifices useful explanatory content, but structurally and stylistically it is very concise.

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?

For a six-parameter tool with no annotations and no schema descriptions, the description is far too incomplete. It does not explain the extraction workflow, how episodes are selected, what force or allow_partial control, or what the output artifacts represent. The output schema may cover return values, but the description still leaves major operational questions unanswered.

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?

The schema description coverage is 0% and the description provides no explanation of any parameter. Confirm, force, allow_partial, max_evidence_per_mention, podcast_id, and episode_ref are all left undocumented in prose. Even though some parameter names are self-explanatory, the description itself adds no semantic value.

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 the tool writes 'deterministic mention artifacts' and that it has side effects, coupling with the name 'extract_mentions.' However, it never explicitly says the tool extracts mentions from episodes, and 'deterministic mention artifacts' is vague jargon. It also does not differentiate itself from sibling tools like search_mentions or validate_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?

No guidance is given for when to use this tool instead of alternatives. The only usage-related information is 'needs confirm=true to write', which is a safety gate rather than a selection criterion. There is no mention of prerequisites, pipeline ordering, or exclusions.

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