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

The description goes far beyond the annotations by disclosing that image quality is unchanged, size reduction is not guaranteed, costs are incurred per started 10 pages, output expires in 10 minutes, and digital signatures can be invalidated. These are non-obvious consequences an agent needs before invoking the tool. There is no contradiction with the annotations.

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?

The description is compact: four short sentences, each adding a distinct operational fact. The primary verb and resource are front-loaded, and there is no filler or redundant restatement of the tool name.

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 an operation with 7 parameters and no output schema, the description leaves important gaps: how the output is returned or retrieved, what the optional parameters do, and whether all fileIds are processed or only one. Cost and side effects are covered, but an agent cannot fully understand invocation semantics from the description alone.

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 only 14%, yet the description explains none of the concrete parameters beyond indirectly noting page limits. fileIds, pages, degrees, title, author, and subject are left unexplained, and saying 'one PDF' while fileIds allows up to 10 items creates ambiguity. The description does not compensate for the sparse 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 opens with a specific verb and resource: 'Losslessly rewrite one PDF with object streams.' It adds decisive scope details—image quality unchanged and no size-reduction guarantee—that make it distinguishable from sibling operations like pdf_merge, pdf_split, and pdf_rotate.

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?

The description supplies operational constraints such as credit cost, 100-page maximum, and 10-minute output expiry, which help an agent decide whether the operation is feasible. However, it never explicitly states when to prefer this tool over a sibling, nor does it name alternatives or exclusions; the compression use case is implied but not stated.

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