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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds behavior those flags cannot convey: the output is a new PDF plus a CSV log mapping page number to Bates number, the first and last Bates number are reported, and every stamp is re-verified in the produced file before a link is issued. It also discloses operational limits (password-protected inputs rejected, single-file scope, Latin-script-only rendering), none of which contradicts 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 text is front-loaded with the trigger condition and use case, then inputs, outputs, verification behavior, hard limits, and finally the sibling exclusion, in roughly the order an agent needs them. Every sentence carries distinct information; none merely restates the title or the schema.

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 8-parameter tool with a nested file object and an existing output schema, the description covers trigger conditions, produced artifacts, verification, and all three hard exclusions, so nothing an agent needs to call it correctly is missing. Return values are covered by the output schema and only summarized here, which is the right division of labor.

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 every parameter already carries its own explanation, defaults, and bounds; the description only summarizes them ('a prefix, start number, zero-padding digits (1-10), optional suffix and one of six positions') without adding format rules such as how prefix plus padding compose. Baseline 3 is appropriate because the schema does the heavy lifting here.

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 ('Bates number a PDF') and immediately gives concrete variants ('Bates stamp documents for a legal production', 'add sequential document control numbers such as ACME000101'), so the agent knows exactly what operation this performs. It also names the sibling it is not ('use stamp_page_numbers'), which disambiguates it from a closely related tool.

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 explicitly enumerates when to use this tool and when not to: no password-protected PDFs, no numbering across several files in one call (pass the next start number yourself), no non-Latin scripts, and no simple page numbers. It also routes the agent to the correct alternative for the page-number case, satisfying the when-not/alternatives bar.

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