DocRaptor MCP by usefulapi

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

With only destructiveHint=true in annotations, the description carries most of the burden and does so well: it discloses that documents are watermarked and Excel capped at 20 rows by default, that test:false consumes billed credits, that hosted mode requires a paid add-on, and that download links can expire. It stops short of describing the async return shape (a status_id field) with the same specificity it gives download_url, leaving one behavioral gap.

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?

Six tight sentences, front-loaded with the core action and input constraint, then escalating to mode selection, cost/limits, and finally the API endpoint. Every sentence carries a decision-relevant fact; nothing is padding.

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 19-parameter mutation with a deep nested object and no output schema, the description covers the highest-stakes branches (billing, watermarking, add-on requirement, sync vs async) which is what an agent most needs. The remaining gap is return-value shape outside of hosted mode — base64 payload size and the async status response are only loosely implied.

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 real meaning: it tightens 'Use this OR document_url' into an exactly-one-of constraint, and it explains the interaction between test, hosted, and async defaults that the schema documents in isolation. It does not attempt to explain prince_options' ~35 sub-properties, which is reasonable given the schema documents them inline.

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 and resource — 'Generate a PDF or Excel document from HTML (document_content) or a URL (document_url)' — and names all three output formats via the title. An agent can immediately distinguish this from the sibling read-only helpers (list_documents, get_document_status, list_ip_addresses).

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 states the selection rule for the two mutually exclusive inputs ('Exactly one of document_content / document_url is required') and then gives decision branches: use default hosted mode for agent-friendly URLs, hosted:false if the add-on is absent, async:true for large jobs with polling via docraptor_get_document_status. It also flags the test-mode default and how to opt out, so there are no hidden surprises before invoking.

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?

readOnlyHint=true already declares the safe-read profile, and the description adds valuable detail on the actual state machine (queued | working | completed | failed) plus what becomes available on completion (download_url / download_id / number_of_pages). Missing only polling/rate-limit guidance, but the added behavioral context is real.

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 tight sentences: the purpose plus the trigger condition come first, then the return payload and the underlying endpoint. No 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?

With no output schema, the description takes on the burden of describing returns and does it, enumerating the possible status values and the completion fields. An agent has everything needed to call it and interpret the result.

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 the single status_id parameter's schema description ('returned by docraptor_create_document when async:true') duplicates what the prose says. With the schema carrying the full load, the 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?

States a specific verb (Check the status) and resource (asynchronous document), and explicitly scopes it to documents created by docraptor_create_document with async:true, which cleanly separates it from the sibling create/list tools.

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 condition for use is clear: it is the follow-up call for an async creation, and the {async:true} reference pins down exactly which create path produces a usable status_id. It does not name an explicit when-not-to-use or alternative, but the context 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?

Annotations already declare readOnlyHint=true, and the description adds genuinely useful context beyond that: the sort order, the pagination nature, the fact that only metadata (not rendered files) persists, and the underlying GET /docs.json endpoint. It does not cover rate limits or default page size behavior, so not a 5.

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 core purpose, and each adds something (scope, non-retention caveat, endpoint). The API endpoint mention is mildly redundant but not wasteful. No padding.

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 describes the return contents (name, type, test flag, creation time) and ordering, which an agent needs. Pagination defaults are left to the schema, and there is no note on total counts or paging termination, so a small gap remains.

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 both page and per_page documented including defaults and max, so the schema carries the parameter burden and the baseline is 3. The description only alludes to pagination generically and adds no format or constraint detail beyond the schema.

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 ('List metadata for documents created on this account') plus the ordering scope (most recent first, paginated), so the agent knows exactly what it returns. It does not, however, distinguish itself from siblings like docraptor_get_document_status or docraptor_create_document, so it stops short of a 5.

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?

Usage is implied — enumerate documents on the account — and the caveat that rendered files are not retained tells the agent what this tool cannot be used for. But no alternative sibling is named and no explicit 'use this when...' condition is given, so this is minimum-viable routing guidance.

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=true, so safety is covered. The description adds genuinely useful behavior beyond that: the IP list changes over time, and the underlying endpoint is GET /ips.json. This is meaningful operational context an agent could not infer from structured fields.

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 tight sentences that front-load what the tool returns and immediately follow with the reason to use it. The parenthetical security note is long but earns its place by discouraging a fragile pattern.

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 read-only, no-parameter list tool with a 100%-covered (empty) schema and no output schema, the description says everything needed: what it returns, why, and the caveat about staleness. Only the exact return shape is unspecified, which is largely self-evident here.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline for a 0-param tool is 4; the description correctly implies no filtering or input is needed.

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 (List) and resource (DocRaptor IP addresses), and scopes it precisely: the IPs used to fetch remote assets/document_url. This is clearly distinguishable from create_document, get_document_status, and list_documents.

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 names the use case (allowlisting DocRaptor on a firewall or asset host) and points toward the preferred alternative (HTTP Basic auth over IP allowlisting). No explicit 'when not to call' clause, but the practical context is clear.

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