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

Annotations only declare readOnly=false, idempotent=true, destructive=false; the description goes far beyond by disclosing cache reuse, that cached results don't consume allowance, per-source quota refusal rules, midnight-UTC reset, plan gating (Revenue Writer+), and that a call costs five rate-limit requests. It also explains the asynchronous processing contract (status processing + transcriptId).

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 purpose and accepted sources, and almost every sentence carries distinct operational information (async flow, cache, quota, rate limit). It is dense — the quota/plan/rate-limit tail is a long run-on that could be split for scanability, which keeps it from a 5.

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 4-parameter tool with an output schema, the description supplies everything an agent needs: input acceptance rules, the async polling path, failure modes (Spotify, exhausted allowance), and cost/plan constraints. Nothing material is left to inference.

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%, so the baseline is 3; the description adds real meaning on top by explaining the url/uploadUrl exclusivity in operational terms and clarifying that episode defaults to the latest when omitted. It does not add anything beyond the schema for maxChars, which caps it below 5.

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 ('Get the transcript') and enumerates the exact source types accepted (YouTube video, podcast RSS, Apple Podcasts link, episode page, direct audio file). The named purpose (quote, summarise, repurpose) plus the explicit handoff to get_transcript_status makes it distinguishable from every sibling at a glance.

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?

Explicitly covers when to use url vs uploadUrl, how episode resolution works for feeds, what to do for long audio (poll get_transcript_status every ~20s), and a hard exclusion ('Spotify links cannot be transcribed'). It also states quota-exhaustion behaviour per source type, so an agent knows which inputs will still succeed.

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