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

Annotations only declare readOnlyHint and openWorldHint; the description adds the things an agent actually needs: a hard 4 MB decoded size ceiling, the credit cost (2 per call), the truncation rule (20 most severe messages, FATAL first), and the exact validity semantics (valid is true only when there is no FATAL and no ERROR). It also spells out the escape hatch to the REST API for larger files.

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, then input constraints, then return shape, then cost, with no filler sentences. The middle paragraph re-describes the response payload in detail even though an output schema exists, which is the one place it spends words the agent may not need.

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 two-parameter read-only validation tool with a nested file object and an output schema, the description covers everything that matters: input modes, size ceiling, cost, validity semantics, and the alternative endpoint for large files. 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 100%, and the schema already documents the 4 MB decoded limit and the download-link semantics, so the description largely restates structured data. It does clarify the either/or relationship between `epub_base64` and `file`, which is the one piece of meaning not obvious from the schema alone, but that is marginal over an already-complete schema.

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?

The description states a specific verb and resource ("Check an EPUB file (EPUB 2 or 3)") and names the exact engine, EPUBCheck, the W3C conformance checker. There are no siblings to disambiguate from, but the scope (spec-conformance validation, not rendering or conversion) is unmistakable.

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?

It gives explicit routing between the two input modes (base64 vs. `file` download link) and states a clear exclusion: files above 4 MB decoded, or a full report, must go to the REST API endpoint, which is named with its path. Nothing about when to pick this tool is left to inference.

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