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

With no annotations, the description carries the full burden. It adds useful context: facts come from transcript extract + domain dictionary, persist in pbx-index, scoped by x-temsor-pbx-key, and mentions constraints like 'Idle $0', 'No DID sales', and 'KVKK forget ready'. However, it does not explicitly state whether the operation is read-only, does not describe error behavior, rate limits, or side effects. This is moderate transparency but not comprehensive.

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 front-loaded with purpose and filtering, then includes an API endpoint and several contextual statements. While not overly long, it contains potentially extraneous notes (e.g., 'Idle $0', 'No DID sales', 'KVKK forget ready') that may not be essential for tool selection. Every sentence adds some context, but the structure could be tighter.

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?

Given no output schema, the description does not explain the return format of the facts list, pagination details beyond the limit parameter, or error handling. It does cover the source of facts (transcript extract + dictionary), persistence, and scoping, which are helpful. However, for a tool with 5 optional parameters and no output schema, more detail on what constitutes a 'fact' and how results are ordered would improve completeness.

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 covers 100% of parameters with descriptions, so the baseline is 3. The description adds little beyond what the schema already provides; it mentions 'filter by call_id, kind, domain, q' but does not elaborate on syntax or special values beyond the example URL that shows domain enum options. This is consistent with the baseline.

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 clearly states a specific verb ('List') and resource ('extracted facts'), and explicitly mentions the filtering dimensions (call_id, kind, domain, q). This distinguishes it from the sibling pbx_facts_get (which likely retrieves a single fact) and other pbx_* tools. The inclusion of an example API endpoint further clarifies the intent.

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?

There is no explicit guidance on when to use this tool versus alternatives such as pbx_facts_get or pbx_search. The description mentions filtering capabilities but does not state when a list operation is preferred over a get or search. It relies on the agent inferring the use case from 'List', which is weak.

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