Faceabot PDF text extractor

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new context: the 10 MB size ceiling, page-by-page return shape, and the 'use start to read further' continuation path. It omits auth/rate-limit notes, keeping it out of 5 territory.

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?

Front-loaded with the core action, then constraints, then an example. The parenthetical 'parse / read a PDF: invoices, papers, reports, contracts, forms…' keyword list is padding, but everything else 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?

With no output schema, the description correctly covers the return shape ('text, page by page'), size limits, and the continuation mechanism, plus the OCR exclusion. Missing only the semantics of max_chars, which leaves one parameter's behavior unstated.

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 75% and the schema already explains url, pages, and start. The description's 'use start to read further' merely restates the schema's own offset wording, and max_chars is undocumented in both places, so the description does not compensate for the remaining gap.

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 ('Reads a PDF ... returns its text, page by page') with the source constraint (public https address). It does not name the sibling pdf_info, so the agent must infer the distinction between text extraction and metadata inspection from the verb alone.

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 when: you need the text content of a PDF file' gives an explicit trigger, and 'Not for scanned PDFs (images only): those need OCR' gives an explicit exclusion with the alternative named. It stops short of routing against the sibling pdf_info, so it lands just under a 5.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the return-shape detail that no output schema provides — that it reports extractability of text — which is genuinely useful for deciding whether to call pdf_extract_text next. It says nothing about authentication, rate limits, or failure behavior for unreachable URLs.

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?

Three short, front-loaded lines: output fields first, then the usage trigger, then an example. Nothing is bloated, though the embedded example call duplicates the example already present in the input schema, which is a small amount of redundant real estate.

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 no output schema, the description carries the burden of describing return values and does so by listing the reported fields. Combined with annotations covering the safety profile and a fully documented single parameter, an agent has what it needs; only the fallback behavior on unreadable URLs is left unstated.

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% with a single 'url' parameter already documented as 'Public https address of the PDF file'. The description adds no new meaning about the parameter — its inline example is identical to the one already in the schema — so the baseline 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 description enumerates exactly what the tool reports (page count, title, author, creation date, text extractability), which is a specific resource-level statement rather than a tautology. It implicitly separates itself from pdf_extract_text by framing the output as 'what a PDF is' rather than its contents, but it never names that sibling, so differentiation is inferred rather than stated.

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 when: you want to know what a PDF is before reading it' gives a clear triggering condition and even implies the ordering (inspect first, then read). It does not name pdf_extract_text as the follow-on alternative or state any exclusions, so it falls short of the explicit when/when-not routing that would earn a 5.

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