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

Annotations cover the safety envelope (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower, but the description adds real lifecycle context beyond them: the declared constraints are labelled 'declared' and are superseded automatically when a measured profile builds. It also instructs 'Ask them in one message; skip any the author does not care about', which is behavioral guidance not present 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 when-to-use condition, then the mechanics, then the question list. Information-dense with no filler, though the parenthetical about the 2,000-word threshold and the trailing instruction make it longer than strictly needed.

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, but the description explains what is produced and how it is later replaced, so the agent understands the state change. The only gap is the return value/confirmation shape, which is minor for a small two-parameter write.

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 would be 3, but the description enumerates the six answer keys and their allowed values (contractions yes/no; person i/we/neither; dashes dashes/commas; formality casual/plain/formal; sentences short/mixed/long), which the free-text 'answers' JSON schema does not constrain. That is meaningful added semantics for a schema with zero enums.

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 ('ask the author six quick questions and save the answers as DECLARED voice constraints') and names the exact artifact produced. It also distinguishes itself from the measured-profile path by spelling out coexistence ('used and labelled declared until the measured profile builds itself'), so an agent can tell it apart from create_voice_profile and get_voice_profile.

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?

Opens with the selecting condition 'No writing samples yet?' and adds a concrete trigger point (automatic once 2,000 words are on file), which tells the agent when this tool is the right one. It stops short of naming sibling alternatives (voice_probe, create_voice_profile) explicitly.

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