Mdkit

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

No annotations provided, so description carries full burden. It discloses the synchronous behavior, the conversion process (decode base64, run markitdown), and the exact return format {markdown, meta}. It does not cover failure modes or auth needs, but the described behavior is adequate for a converter 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?

Two concise paragraphs with clear front-loading. The first sentence states the core purpose, and the rest adds necessary detail. No wasted 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 an output schema exists (so return structure is documented elsewhere), the description provides key context: synchronous execution, base64 decoding, markitdown usage, and sibling differentiation. It lacks detail on error handling or supported formats, but it's largely sufficient for a simple converter.

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 0%, so description must compensate. It explains content_base64 as 'the raw file bytes, base64-encoded' and filename as the source (appearing in meta). This adds meaning beyond the bare schema, though it could be more explicit about file format or size constraints.

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 'Convert a document to Markdown synchronously' and specifies it as the 'fast lane'. It distinguishes itself from sibling tools by naming the alternative for large/complex 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?

Explicit guidance: 'Best for small office/HTML/text files; for large or complex documents (or OCR-heavy PDFs) use submit_conversion_job instead'. This directly tells the agent when to use this tool versus the sibling.

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 fully discloses key behaviors: response structure, scoping to caller's identity, handling of success (inlined vs. URL), and error details. This provides transparency without contradiction.

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 purpose, and includes essential behavior details without unnecessary words. 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 the tool's simplicity (one parameter, output schema assumed), the description covers purpose, scope, status outcomes, and result handling. It is complete for an AI agent to use correctly.

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 only parameter 'job_id' lacks schema description (0% coverage), but the description adds meaning by stating it must be a job submitted by the caller and that others return not found. This compensates well.

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 checks the status of an asynchronous conversion job submitted by the user. It differentiates from sibling tools 'convert_document' and 'submit_conversion_job' by focusing on status checking, with scope limited to the calling identity.

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 after submitting a job and clarifies that it only works for jobs owned by the caller. It lacks explicit when-not to use or alternatives, but the context is clear enough for correct selection.

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 fully discloses behavior: stores bytes, enqueues job, costs 10 credits charged immediately, returns specific fields, poll alternative, webhook callback, requires API key, raises if backend missing. This is comprehensive.

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 well-structured with a clear main verb, bullet points for key details, and no redundant text. Slightly verbose in listing return fields but acceptable.

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 the tool's complexity (async job, cost, error conditions, output schema), the description covers most aspects: purpose, return value usage, error cases, and alternative. Missing details on parameter constraints but overall adequate.

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 0%, yet the description only adds minimal context: filename is for identification, content_base64 is the bytes, webhook_url for callback. It does not explain format constraints or how each parameter affects behavior, leaving gaps for an AI agent.

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 'Submit a document for asynchronous, high-fidelity conversion (docling)', specifying the action, resource, and asynchronicity. It distinguishes from siblings 'convert_document' (likely synchronous) and 'get_conversion_job' (polling).

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 (async conversion), mentions prerequisites (API key, backend config), and how to get results (poll with get_conversion_job or webhook). It does not explicitly contrast with convert_document, but the context is clear enough.

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