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

With no annotations, the description carries the full burden. It discloses the page-by-page iteration for reliability and the detailed return behavior: 'Returns ok:false with unknown_fields if ALL provided field names are invalid' and 'Returns ok:true with a warnings.unknown_fields list if SOME names are invalid (partial fill).' It does not mention side effects like overwriting the source file, but the output_path parameter implies a new file is created. This is strong transparency, though not exhaustive.

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 moderately long but well-structured with WORKFLOW, usage, and returns sections. Every sentence earns its place, including the reliability rationale and the partial-fill warning. It is not as tight as a one-liner, but the length is justified by the tool's complexity and the need to steer agents away from guesswork.

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?

Given the tool's complexity (multi-page form filling, 5 params, nested object, output schema), the description is remarkably complete. It explains the prerequisite step (list_form_fields), the coordinate-based field disambiguation, the conditions for preferring this over fill_form, and the exact return behavior for full vs. partial failures. The existence of an output schema lowers the need to describe return values, but the description still provides a useful summary.

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 baseline is 3. The description enriches parameter meaning by instructing how to determine field_values: use list_form_fields to get exact names and x/y positions, and confirm fields via coordinates. It also warns against guessing field names, adding context beyond the schema's own description. This justifies a 4.

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+resource+scope: 'Fill a multi-page PDF form, iterating page-by-page for reliability.' It clearly distinguishes from sibling fill_form by specifying when multi-page is the appropriate choice (more than 5 pages or fields spanning multiple pages). The workflow ties it to list_form_fields, reinforcing its unique role.

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 guidance is given: 'Use when the PDF has more than 5 pages or fields spanning multiple pages' and 'Prefer this over fill_form for any complex/long document.' The WORKFLOW section instructs to call list_form_fields first and never guess field names, providing concrete when-to and when-not-to usage relative to alternatives.

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