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

Beyond the readOnly/idempotent/closed-world annotations, it discloses the return shape ('each finding with a severity and a suggested fix'), the side effect of surface=slide (withholds a pass pending screenshot review), and an explicit capability limit ('a pass is not visual approval'). That is substantially more than the annotations carry.

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-loads the three tests before the input guidance and return description, with almost no filler. The closing sentence about 'Better Design runs the checks itself and calls no other API' is slightly opaque and arguably does not earn its place.

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?

With seven parameters, no output schema, and a nuanced mode switch (screen vs slide), the description covers inputs, the one enum's behavioral effect, the return content, and the tool's limits. Nothing needed to call it correctly is missing.

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 already 100%, so the baseline is 3, but the description adds real meaning: knownTerms is framed as 'words the audience already knows' so they aren't flagged, and surface='slide' is tied to the density test. It also clarifies the copy-vs-markup input choice that the schema only implies via the code description.

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 ('Checks interface copy for clarity') and enumerates the three tests it applies, so an agent knows exactly what the tool evaluates. No sibling tool covers copy comprehension, and the description makes that scope unambiguous.

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?

Explains what to pass ('the headline, body and action labels, or the markup') and when a variant applies (surface: 'slide' adds a density test). It also sets a clear exclusion ('reads text only, not screenshots or visual hierarchy'), though it never routes the agent to a sibling for the visual-review case it declines.

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