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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavior: no credit consumed, the score_context caveat array that prevents misreading structurally low scores, the reporting rule to cite deltas rather than invent detail, and the 20+ word minimum. That is context an agent cannot get from the structured fields.

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 mechanism before the return-value detail, and most sentences carry information an agent needs (thresholds, caveats, reporting rule). It runs long and has mild redundancy around the deltas/notes relationship, but nothing is pure filler.

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 correctly carries the full return-shape burden and does so: voice_match_score range, deltas array contents, notes provenance, and score_context caveats. Combined with the input constraints and usage scale, an agent has everything needed to call and interpret it.

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% (baseline 3), but the description adds a real constraint the schema does not express: the schema declares minLength 1 while the prose requires 20+ words and ~50k char ceiling. It also clarifies profile_id must be a 'complete' profile, which is more specific than the schema's plain uuid format.

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 ('Score any text against a voice profile') and explains the mechanism (stylometric feature-delta measurement) in concrete terms. It is clearly distinguishable from most siblings, but never names the obviously adjacent sibling compare_voice, leaving an agent to infer which of the two to reach for.

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?

Gives a clear use context ('verify drafts you wrote yourself and iterate') and useful scale interpretation (0.85-0.95 on-voice, 0.5-0.8 partial, <0.45 off-voice). However it offers no explicit when-not-to-use condition and does not route the agent away from compare_voice, so the guidance is clear but not discriminating.

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