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

Beyond the annotations it discloses material behavior: the mark is drawn on a copy (original untouched), the download is retained about 1 hour, each mark is verified to be in the file, and there is no certificate, identity check or audit trail. That is exactly the extra context annotations cannot carry. The only gap is that readOnlyHint=true sits slightly uneasily with producing a new signed artifact, and the description does not reconcile that beyond saying it works on a copy.

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 trigger conditions come first, then the mechanics, then the limitations — good front-loading with no filler sentences. It runs long and packs several ideas per sentence, but each one (retention window, verification, certification caveat) earns its place.

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 10-parameter nested-schema mutation tool with an output schema, the description covers the gaps that structured fields cannot: it explains the copy-and-download model, the one-hour retention, and the legal/technical limits of the signature. Nothing an agent needs to call this safely is 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%, so every parameter including the nested placement fields is already documented with examples. The description adds little parameter-level detail beyond restating the four mark kinds and noting the SVG path comes from 'the widget pad', so the baseline of 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 opening sentence names a specific verb and resource ('sign a PDF') and enumerates the variants (signature, initials, date, typed name). It distinguishes itself from the sibling by pointing to find_signature_spots as the source of spot ids, and it explicitly states what it is not (certified digital signature, form filler, sender).

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 gives explicit triggers ('when the user wants to sign a PDF, e-sign a document, add a signature, initials or a date'), an explicit hand-off to find_signature_spots for locating spots, and explicit exclusions ('do not use for certificate-based digital signatures or for signing on someone else's behalf without consent'). An agent has no inference left to make about routing.

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