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

Annotations already declare read-only and non-destructive, so the bar is low. The description adds real value: it states the response is links and text, never audio, and pins the backing endpoint (GET /leads/{lead_id}), disclosing the data source and the shape of the return.

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?

Content is front-loaded with the returned fields first, then the audio caveat, then the endpoint provenance. Dense but every clause carries information; the parenthetical about the audio endpoint is slightly tangential but justified.

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?

With no output schema, the description carries the burden of describing return values, and it enumerates the returned fields (links, duration, answer status, numbers, transcripts) explicitly. For a single-parameter read tool, nothing an agent needs 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% with a single self-documented lead_id parameter, so the schema does the heavy lifting. The description adds no lead_id format or constraint details beyond it, matching the baseline for fully covered params.

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?

Specific verb (get) plus resource (call recording info) and a full enumeration of what it exposes: recording/voicemail links, duration, answer status, tracking/caller numbers, transcripts. It also distinguishes itself from the sibling get_lead by scoping to recording/voicemail facts, so an agent can route without opening schemas.

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 clarifies the audio boundary ('returns links and text only, never audio') and notes the raw MP3 endpoint is not used, which steers the agent away from expecting audio. It stops short of naming a sibling tool or explicitly saying when to prefer get_lead instead, so it lacks full alternative routing.

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