Zovo PDF Maker

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real value beyond that — the fallback build-from-text behavior and the reported outcome (blocks found in order, missing, out of order) — though it does not mention limits, size constraints, or failure modes for unreadable PDFs.

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?

Four sentences, front-loaded with the usage trigger, then mode behavior, then the scope boundary. Nothing is padded; the closing 'compares text only' sentence is the highest-value line and is kept short.

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?

With an output schema present, the description needn't explain return values, and it doesn't over-explain them. Given 10 parameters, nested file object, and a sibling make_pdf, the description covers the mode distinction and comparison scope that structured fields cannot express.

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 the baseline is 3, but the description adds non-obvious semantics for the optional file object: supplying it checks that file, omitting it triggers a build-and-check path. It also clarifies what 'text' means (Markdown whose blocks should appear), which the schema alone does not convey.

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?

States a specific verb and resource — confirm that Markdown text blocks (headings, paragraphs, list items, table cells, code) are present in a PDF in the same order. The ordering-of-blocks criterion separates it cleanly from make_pdf, which it names explicitly.

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?

Opens with a direct when-to-use clause ("when the user wants to confirm..."), then explains the two operating modes (with an uploaded PDF vs. building one as make_pdf does), and closes with explicit exclusions: no fonts, layout, images, spelling, and no PDF editing.

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

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the return payload (both links, page count, outline with page numbers, a read-back text check) and the critical operational caveat that links expire in about 1 hour. It also states the fallback behavior for unsupported Markdown (printed as plain text and listed in notes), which is behavior no annotation or schema conveys. Nothing contradicts readOnlyHint, since no pre-existing content is modified.

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?

It is front-loaded with the use case, then capabilities, then options, then returns, then exclusions and the expiry caveat, so an agent can stop reading at any point. The Markdown feature list is long but each item informs a real formatting decision, leaving little genuine waste.

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 9-parameter generation tool with full schema and an output schema, the description covers the remaining risk surface: what syntax renders, what happens to the rest, size/pagination options in prose, artifact lifetime, and what comes back. An agent needs nothing else to call it correctly or to explain the result to a user.

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 all nine parameters, enums and defaults are already documented in structured form; the description's option recap (Letter/A4, normal/narrow, 10-14 pt, title page, contents, page numbers) largely repeats it. The one genuine addition is that heading parsing covers ATX levels 1-4 and that contents lists levels 1-3, which clarifies how text interacts with format and table_of_contents. Baseline 3 is appropriate.

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 names a concrete verb and dual artifact ("as a downloadable PDF and an editable Word (DOCX) file") and enumerates exactly which Markdown constructs are honored versus printed as plain text. An agent can distinguish this typesetting tool from the sibling check_pdf_text purely from the text, since it explicitly frames its own read-back as a validation extra rather than the tool's purpose.

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?

"Use this when the user wants Markdown or plain text ... as a downloadable PDF and an editable Word file" gives a clear triggering condition, and the closing sentence supplies explicit exclusions (no writing/editing content, no image embedding, no conversion of existing Word/HTML/scans). It stops short of naming an alternative tool for the excluded cases (e.g. check_pdf_text for verifying an existing PDF), so it is a strong 4 rather than a 5.

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