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

Beyond the annotations (destructiveHint=false, openWorldHint=true), the description discloses the real operating constraints: a 5-page-per-document cap, a 30-90 second runtime, and the id/get_translation polling fallback. It also says numbers are kept and checked and that RTL sources can be mirrored, which the annotations cannot convey. It does not say what happens on failure or over-limit documents.

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?

Purpose and output are front-loaded in the first sentence, followed by use cases, triggers, inputs, and limits in a sensible order. The long enumeration of document types (payslips, bank statements, certificates, diplomas, contracts, leases, forms) is verbose but does real routing work for intent matching.

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?

There is no output schema, yet the description fully specifies the return: the same document as a PDF with layout, tables, logos and numbers preserved, plus the async id path for long runs. Combined with input constraints (5 pages, 30-90 seconds) and the mutation-free annotation profile, an agent has everything needed to call it correctly.

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 description coverage is 100%, so the schema already defines every parameter including the layout enum and keep_logos. The description only restates the file vs file_url choice ('a file the user attached' or 'an https link') and mentions RTL mirroring, adding marginal meaning rather than new syntax or constraints, so the baseline 3 applies.

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 first sentence names a specific verb (translates) and resource (PDF/scanned document), and states the output shape (same document returned as PDF with layout preserved). It is clearly distinguishable from siblings: get_translation is named as the async continuation, and convert_to_word is implicitly excluded by the PDF-in/PDF-out framing.

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 trigger phrases ('translate this PDF / document / scan', 'keep the formatting / layout', 'give me back the PDF') plus a negative condition (when a chat translation lost tables or layout) tell the agent exactly when to route here. It also states the fallback path: if the call exceeds 30-90 seconds, an id is returned for get_translation.

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