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

No annotations are provided, so the description carries the burden. It discloses that the tool is heuristic, that it can create Promise docs with status=open, and that persist_promises=false avoids writing. It also lists example trigger words. However, it does not disclose failure modes, confidence levels, idempotency, or what happens to duplicate promises, which are relevant for a heuristic extractor.

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 core purpose, then adds the key behavioral option and integration note. The example trigger words are useful but slightly noisy. Overall, every sentence earns its place, though the structure could be tightened.

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 tool with 6 parameters, no output schema, and no annotations, the description gives the essential purpose and the most important flag, but it omits context about the optional parameters and the shape of the created Promise docs. An agent could call it correctly for the basic case, but would be guessing about the optional metadata fields and the exact return value.

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 33%, so the description must compensate. It explains the transcript parameter's role and the persist_promises flag's dry-run behavior, which adds meaning beyond the schema. However, it does not clarify the ext, who, pbx_id, or call_id parameters, leaving their purpose to inference. The description adds some value but does not fully cover the parameter semantics gap.

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 verb and resource: 'extracts promise-like sentences from transcript text' and 'creates open Promise docs'. It distinguishes itself from siblings by noting it is wired via utterance text on POST /v1/pbx/events, which helps differentiate it from other pbx_* tools. However, it does not explicitly name a sibling alternative, so it falls short of full differentiation.

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?

The description implies usage: use this tool when you have transcript text and want to detect promises, optionally persisting them. It mentions the persist_promises=false dry-run option, which gives some conditional guidance. It does not explicitly state when not to use it or name alternatives among the many pbx_* siblings, so usage guidance is only partially developed.

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