Fluff

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real value: it promises determinism ('same text always gives the same result') and explicitly states the tool does not rewrite. The missing piece is any note on cost or handling of the 60,000-character ceiling, which lives only 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?

Three sentences plus an example, front-loaded with the trigger condition, then the detection criteria, then the return shape. Every clause carries information an agent needs; nothing is repeated from annotations or the schema.

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, and the description compensates by naming all four return components. For a single-parameter, read-only analysis tool, there is nothing further an agent needs in order to invoke it correctly and interpret the result.

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?

With one required parameter at 100% schema coverage, the baseline is 3. The description goes slightly beyond by supplying a concrete invocation example mapping the parameter to its intent ('<the draft to tighten>'), which clarifies that the input is a draft, not a finished artifact.

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 ('flags sentences that are pleasantries, buzzwords, throat-clearing...'), and enumerates the exact outputs (fluff percentage, verdict, flagged sentences with why, recurring filler phrases). An agent knows precisely what it gets back without opening any schema.

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 an explicit trigger: 'Use when the user asks to tighten, shorten or cut the fluff... or asks how much of a text is filler.' It also draws the responsibility boundary with 'Rewrite the flagged parts yourself,' telling the agent what this tool will not do. No siblings exist, so no alternative routing is needed.

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