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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, so the safety and remote-access profile is covered. The description adds the accepted input forms (path, base64 data, https URL) and the metadata returned, but it does not add deeper behavioral context such as error behavior, authentication needs, or rate limits. A 3 is appropriate given the annotation coverage.

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 two tightly written sentences with zero waste. It is front-loaded with the core purpose and then the field list, followed by the supported input forms, making it easy for an agent to scan.

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 simple read-only metadata tool with full schema coverage and no output schema, the description is complete enough: it names the extracted metadata fields and the three supported input forms. Annotations cover the safety profile, and no critical calling detail 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 description coverage is 100%, so the input schema already fully documents path, data, and url, including the 8 MiB limit and the 'exactly one' constraint. The description reinforces that the PDF can be a root-folder path, base64 data, or https URL, but it does not add syntax or format details beyond what the schema provides. Baseline 3 is correct when the schema does the heavy lifting.

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 uses a specific verb and resource: 'Describe a PDF,' and immediately enumerates the metadata fields returned. This clearly distinguishes it from sibling tools like pdf_text, pdf_render_page, and pdf_search, which imply content extraction, rendering, and searching rather than metadata inspection.

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?

The description gives clear context for when to use the tool: to obtain PDF metadata such as page count, title, author, dates, encryption status, and file size. It does not explicitly name alternatives or state when not to use it, so it falls short of the top score, but the intended use case is unambiguous.

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 annotations, the description discloses the dpi ceiling and default, the three accepted source forms, the writable-server prerequisite for save_as, and the PDFium runtime dependency — all real operational context. It also implicitly surfaces a tension with readOnlyHint=true by admitting an optional file write, but it does so honestly and gates it behind save_as, so the agent is not misled.

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 sentences, front-loaded with the action and return type, then inputs, then the optional side effect and dependency. Dense and largely waste-free, though the parenthetical dpi and source phrasing compresses several distinct facts into one sentence.

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 states that an image is returned, and it covers sources, resolution, and the optional save path. Only edge behavior — out-of-range page numbers, fetch failures on url/data, overwrite semantics beyond the schema default — goes unmentioned, which is minor for a 7-param tool with full schema coverage.

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 is already documented with defaults and limits; the description mostly restates the dpi range and the path/data/url choice. It adds a little meaning by framing save_as as an optional extra that requires a writable server, but no more than that.

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 first clause gives a specific verb and resource ('Render one PDF page to a PNG image') plus the output format, so the tool is unambiguous. It implicitly separates itself from pdf_text by offering 'read a scanned page' as the motivating case, but it never names the sibling tools to make the distinction explicit.

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?

'e.g. to read a scanned page' gives one concrete scenario that hints at when to prefer this over pdf_text, which is useful. There is no explicit statement of when not to use it, no named alternative, and no guidance on choosing among the three mutually exclusive PDF sources beyond the schema's own note.

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 cover read-only, open-world, and idempotent behavior, and the description adds real value on top: it discloses the return shape, that hidden-text pages produce warnings, and an explicit prompt-injection caution that snippets are data, not instructions. It omits the 8 MiB fetch cap, but the schema carries that.

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?

Two compact sentences, front-loaded with what is searched and where, followed by the return/warning semantics. No filler, no restated field names.

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 does the necessary work of explaining what comes back (file, page, snippet) and adds a hidden-text warning. Pagination/cap behavior is delegated to the schema, which is reasonable, so the only minor gap is anything about hit limits or result volume.

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 all seven parameters are already documented in the input schema; the description only restates the glob example and the 'exactly one of path/data/url' rule that the schema already states. Baseline 3 is appropriate since the schema does the heavy lifting.

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 (search a PDF) and enumerates the three input modes (glob path, base64 data, https url), with the return being file/page/snippet. The purpose is unambiguous, though it never names pdf_text or pdf_info to mark the boundary between searching and extracting.

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?

The description implies when the tool applies (finding text or a regex across one or many PDFs) and implies the three mutually exclusive input modes, but gives no explicit when-not guidance or comparison against siblings like pdf_text or pdf_info.

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?

Goes well beyond the readOnly/idempotent annotations: it discloses the dual extraction backend (PDFium vs built-in) and that the output reports which was used, warns about invisible/white-on-white/tiny/off-page text, and explicitly frames extracted text as data rather than instructions — a real prompt-injection safeguard.

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 tight sentences, front-loaded with the core action, then inputs, then backend behavior, then the safety note. No filler and nothing buried.

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 return-value burden and does so partially — it says output is page-by-page, reports which extractor ran, and includes hidden-text warnings. It stops short of describing the exact response shape (e.g. how pages are delimited, truncation signaling for max_chars).

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 all five parameters are already documented, including the page-range syntax and the 8 MiB limits. The description restates the page-range example and the three source modes but adds no syntax or constraint detail beyond the schema, so 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?

Opens with a specific verb+resource: 'Extract the text of a PDF, page by page.' That is clearly distinct from pdf_info, pdf_render_page and pdf_search, though the description never names those siblings to reinforce the distinction.

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 explains the input modes and the optional page range, which implies when the tool applies, but it never states when to prefer pdf_search or pdf_info over this, nor any exclusions. Usage is implied rather than guided.

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