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

With no annotations, the description carries the full burden and does solid work: it discloses the heuristic/no-LLM approach, the $0 idle cost, that writes create Promise docs with status=open, and that a dry-run mode exists. It omits permissions, idempotency/duplicate handling, and rate limits, so it is not exhaustive, but the behavior is genuinely informative.

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 paragraphs with the core action front-loaded before the caveats and alternate entry point. Nearly every clause carries information; the only redundancy is re-explaining persist_promises already covered by the schema.

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?

No output schema exists, so the description should describe what comes back (how many promises, their shape), and it does not. Combined with 33% parameter coverage and no annotations, an agent knows what the tool does and its cost model but not what it returns or how the identity parameters (who, pbx_id, call_id, ext) affect the write.

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 coverage is only 33% – four of six parameters (ext, who, pbx_id, call_id) are undocumented in both schema and description, and the description never explains them. Its only parameter statement restates the schema's own persist_promises text, adding no new semantics. With low coverage the description should compensate and it does not.

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+resource: a heuristic extractor that creates open Promise docs from transcript text, with the useful qualifier 'no LLM, idle $0'. That is far more specific than a tautology. It stops short of naming a sibling (e.g. pbx_promises, pbx_index_partial) to differentiate, so it lands at 4 rather than 5.

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 one concrete usage lever – persist_promises=false for extract-without-writing – and notes an alternate entry point (utterance text on POST /v1/pbx/events). But it never says when an agent should reach for this tool versus pbx_promises, pbx_index_partial, or pbx_events. Usage is implied rather than stated, which is the definition of a 3.

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