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

Annotations declare destructiveHint=true and idempotentHint=true, and the description goes well beyond them: crop 'removes everything inside the margin band, so that content is NOT printed', the original upload is kept, and re-calling with the other mode replaces the earlier fix. It also discloses a lifecycle constraint not in annotations (fails once the letter is paid), which is exactly the kind of context the agent needs before invoking a destructive fix.

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 triggering condition and mode semantics, and each sentence carries a distinct constraint (destruction, reversibility, lifecycle, escalation). It is dense — several clauses packed into long sentences — but no sentence is 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?

For a destructive, non-read-only operation with no output schema, the description covers what gets removed, what is preserved, reversibility, the paid-letter precondition, and the auth requirement. Nothing an agent needs to call this correctly appears to be 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 mode enum is already fully documented in the schema, so the baseline is 3. The description earns extra credit by adding behaviour the schema does not: how shrink centres pages ('US Letter for a US Letter PDF, else A4') and how mixed PDFs that already fit on A4 keep their placement.

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 (fix) and resource (document margins) and pins the exact trigger condition: an uploaded PDF that fails the print check because content is too close to the edge or pages are not A4/US Letter. This distinguishes it from check_pdf_margins (the diagnostic) without opening either 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?

Explicit when-to-use (print check failure), when-not-to-use (not possible once the letter is paid), and an escalation rule (ask the user which mode they prefer when content touches the edge). It also specifies the precondition 'Needs the user's account', leaving little to inference.

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