doc.page PDF Extraction

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

With no annotations provided, the description carries full burden. It discloses the link is tracked, belongs to the account, appears in the library, requires an API key, free plan limits, optional expiry, and open-notification toggle. Missing details like rate limits or exact authentication mechanism, but acceptable for a creation tool.

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 sentences, front-loaded with the main action, and includes essential details like limitations and options without fluff. Every sentence adds value.

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?

Given no output schema and no annotations, the description covers return value (shareable URL), constraints (max PDF size, active links limit), and optional parameters. It is sufficiently complete for the tool's complexity.

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 schema already documents all parameters. The description only summarizes optional expiry and notify toggle. 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 clearly states the tool publishes a PDF as a tracked doc.page Doc Link and returns a shareable URL. This specific verb+resource distinguishes it from sibling tools like list_doc_links (which lists) and revoke_doc_link (which revokes).

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 context on when to use (publishing trackable PDF links) and includes limitations (free plan: 3 active links, premium-only vanity slugs). It does not explicitly state when not to use or compare to siblings, but the sibling names imply distinct purposes.

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?

With no annotations, the description carries full burden. It discloses that 'hybrid' is heavier, reconstructs tables/bounding boxes, and that 'fast' is prose-only with low confidence on tables. However, it does not mention side effects like read-only or rate limits.

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 sentences: the first states the core purpose, the second explains mode options. No unnecessary words.

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?

Given no output schema, the description covers all parameters and their defaults. It lacks details on the return format beyond 'ExtractedDocument object' and does not mention error conditions or limitations, but is adequate for a tool with 4 parameters.

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?

The description adds significant meaning beyond the schema: it explains the difference between modes in depth, states the default for 'mode' (fast) and 'outputs' (markdown and elements), and clarifies fallback behavior for hybrid.

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 clearly states the verb 'extract', the resource 'PDF', and the outcome 'clean Markdown and structured elements'. It also distinguishes from siblings by focusing on full document extraction versus other tools like list_tables.

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 explains when to use 'fast' vs 'hybrid' mode based on the need for tables and bounding boxes. It provides clear context but does not explicitly state when not to use the tool or compare to alternatives among siblings.

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?

With no annotations provided, the description carries full burden. It describes the output structure (text, tokens, page, heading, element ids) but does not disclose potential side effects or whether the operation is read-only. The description adds context beyond annotations but lacks some behavioral details.

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 a single, well-structured sentence that front-loads the action and purpose. Every word contributes meaning with no redundancy or filler.

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?

The description explains the tool's purpose, output contents, and use case. It lacks details on error handling, size limits, or streaming, but given the simplicity (2 parameters) and lack of output schema, the description is fairly complete.

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 schema already documents parameters. The description adds context about the output but does not add specific meaning about parameters beyond what is in the schema. Baseline score of 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 clearly states the action ('Split a PDF into semantic chunks') and the purpose ('ready for embeddings (RAG)'). It distinguishes from sibling tools like extract_pdf and list_tables by specifying the chunking for RAG use case.

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 use when chunks for embeddings are needed but does not explicitly state when to use this tool versus alternatives like extract_pdf or list_tables. No exclusions or when-not-to-use guidance provided.

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?

With no annotations, description fully covers behavior: always returns summary fields, premium plans get additional data, include parameter adds visits rows. Does not explicitly state it's read-only or mention rate limits, but overall transparent.

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?

Single concise paragraph with clear structure: purpose, always-returned fields, premium specifics, parameter guidance, authentication requirement. Every sentence adds necessary information without redundancy.

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?

No output schema, but description sufficiently explains return values (summary, premium extras, visits rows) and conditions. Complete for an analytics tool with conditional enrichment, leaving no major gaps.

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%, but description adds value by explaining that id and slug are alternatives, clarifying include parameter purpose ('recent visit rows'), and detailing premium enrichment. Provides context beyond schema defaults.

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?

Description clearly states it reads analytics for one Doc Link, specifying verb, resource, and scope (by id or slug). Differentiates from siblings like create_doc_link and list_doc_links by being read-only analytics.

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?

Description indicates when to use (retrieving analytics for a single doc link) and notes API key requirement. It implies premium vs non-premium behavior but does not explicitly exclude alternatives or provide when-not scenarios.

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?

No annotations provided, so description bears full burden. It describes scope and fields but does not disclose read-only nature, rate limits, or error behavior. Adequate but could be improved.

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 efficient sentences with no redundancy. Action verb and key details front-loaded.

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?

Given zero parameters and no output schema, description covers purpose, usage context, and authentication. Lacks minor details like empty result behavior, but sufficient for simple list tool.

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?

No parameters, so schema coverage is 100%. Baseline for 0 parameters is 4; description doesn't add parameter info because none exist.

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?

Description clearly states the verb 'List', the resource 'Doc Links of the API key's account', and enumerates returned fields. It distinguishes from siblings like create_doc_link and get_doc_link_stats.

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?

Explicitly says 'Use this to recover links created in earlier sessions before querying stats,' providing specific context and sequence. It mentions the API key requirement but doesn't explicitly state when not to use.

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?

No annotations are provided, so the description must cover behavioral traits. It mentions the engine type ('semantic hybrid') and output structure but omits side effects, auth requirements, rate limits, or behavior on non-table PDFs. Partial transparency.

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 sentences front-load the primary purpose and output details. Every word is informative with no fluff. The structure is efficient and easy to parse quickly.

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 tool with one parameter and no output schema, the description covers what it returns and the engine choice. It lacks mention of potential limitations (e.g., page range, table detection accuracy), but overall provides sufficient context for expected use.

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?

With 100% schema coverage and only one parameter already described in the schema, the description adds no further semantic value. The baseline score of 3 applies, as the schema carries the full parameter definition.

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 clearly defines the tool's action: returning tables from a PDF as structured JSON with location metadata. It uses specific verbs ('Return every table') and distinguishes from sibling tools like extract_pdf by specifying the output format and added citation capability.

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 usage for extracting tables with citations but does not explicitly state when to use this over siblings (e.g., extract_pdf for full text, get_chunks for content fragments). No exclusion criteria or prerequisites are mentioned.

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?

In the absence of annotations, the description provides key behavioral details: the public URL stops serving, item and stats remain, and a free plan slot is freed. It also mentions the API key requirement. However, it does not disclose if the action is reversible or any error conditions.

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 concise sentences, each serving a distinct purpose: action description, persistence/slot note, authentication. No redundant or extraneous content.

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?

While the tool is simple and the description covers the main behavior, it lacks information about return value (no output schema), potential errors, or behavior when both id and slug are provided. Adequate but not comprehensive.

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% and already explains both 'id' and 'slug' parameters. The description adds only minor context (API key's account) beyond what the schema provides, so it meets the baseline for high coverage.

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?

Description clearly states the verb 'Disable' (matching the name 'revoke') and the resource 'Doc Link', specifying that it stops the public URL from serving. It distinguishes from sibling tools like create_doc_link, get_doc_link_stats, and list_doc_links by focusing on the revoking action.

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?

Description implies usage when you need to stop serving a public URL and notes a contextual benefit (frees slot on free plan), but does not explicitly state when not to use this tool or suggest alternatives like deleting the link entirely or using other tools to manage links.

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