Fetch the call transcript (phone path, step 2 of 2)

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

With no annotations, the description carries the full burden and does so: it discloses the blocking wait (up to ~3 minutes per call), the retry/idempotency pattern, the mutation (transcript stored against the brief), and a consent-validation side effect (AI disclosure, permission to record, subject's yes). These are exactly the behaviors an agent needs to plan around, none of which appear in the schema.

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?

Front-loaded with the step position and the core action, then the operational loop, then the handoff. Nearly every sentence earns its place, though the normalize/consent-check detail is slightly more than needed to select and invoke the tool.

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 must explain return values, and it does: the two terminal answers (STILL IN PROGRESS vs TRANSCRIPT STORED) are named verbatim. Combined with the wait semantics and next-step routing, an agent has everything required to call it correctly and repeatedly.

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 100% and the schema itself richly documents brief_id and wait_secs, so the baseline is 3. The description adds real meaning on top: 'up to about three minutes per call' and 'a ten-minute interview needs about four calls' directly explain the wait_secs default of 170 and its retry economics, which is more than the schema's terse note provides.

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 and resource (fetch transcript) plus the full pipeline: waits for the call to end, pulls from ElevenLabs, normalizes to timestamped turns, runs a consent check, stores against the brief. It also positions itself in the workflow ('step 2 of the phone path') and names the predecessor (place_call, via brief_id) and successor (draft_piece), so it is unmistakable against siblings.

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?

Explicit when-to-call and when-to-call-again: if the answer is STILL IN PROGRESS, call it again as many times as needed until TRANSCRIPT STORED, with a concrete expectation ('a ten-minute interview needs about four calls'). It also hands off the next step ('Then: draft_piece'), so the agent knows both the loop condition and the exit path.

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