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

With no annotations provided, the description carries the full burden of behavioral disclosure. It covers key side effects: the 'force' parameter indicates overwrite behavior, 'allow_remote' reveals remote image fetching is opt-in, and it explicitly states it returns metadata plus an inline file. It does not mention error handling or permission requirements, but it provides enough behavioral context for an agent to call it safely.

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 front-loaded with the core purpose, then lists each parameter concisely in a consistent format. It is moderately long due to 7 parameters, but every sentence earns its place—no filler. The structure is easy to scan and the argument explanations are tight.

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 thoroughly covers parameters but is vague about the return value ('metadata plus the inline file') without specifying what metadata contains. It also does not mention error cases, idempotency, or whether validation is required before calling. Given the lack of an output schema and the tool's complexity, more detail on return structure and potential failures would be helpful.

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 the description is the only source of parameter meaning. It explains each of the 7 parameters with defaults, purpose, and examples (e.g., 'theme: Override the spec theme (e.g. default, report, invoice)'). It even clarifies the spec format via a resource reference. This fully compensates for the schema's lack of descriptions.

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 opens with a clear, specific statement: 'Render a document spec to a PDF and return metadata plus the inline file.' It names the verb (render), resource (document spec), and output (PDF). It distinguishes from siblings like validate_spec (validation) and from_markdown (likely conversion), leaving no ambiguity about what this tool does.

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 to use this tool (to generate a PDF from a spec) but never explicitly contrasts it with validate_spec or from_markdown, nor says when not to use it. It references a spec schema resource, which hints at prerequisites, but there is no direct guidance on alternative selection. This is a clear gap for a tool with 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, the description carries the full burden and does a solid job. It discloses defaults (author, home, out, base_dir), special behaviors (footer placeholders, force overwrites, allow_remote), and states that output includes metadata plus an inline file. However, it omits side effects like file creation details, error behavior, and any authorization requirements, leaving some behavioral gaps.

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 efficiently structured: a one-sentence summary followed by a bulleted argument list. Each parameter gets a single line, making it scannable. It is slightly long due to the number of parameters, but every line earns its place; no fluff or repetition.

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 13 parameters and no output schema, the description covers all parameters and mentions the return type, but leaves important context missing. It doesn't specify the structure of 'metadata' or how the 'inline file' is returned, nor does it address error conditions or usage context relative to siblings. An agent might need to probe to understand full invocation behavior.

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%, and the description compensates exceptionally well. It explains every parameter's meaning, provides defaults, and includes specific syntax details (e.g., footer supports {page} and {pages}, out defaults to <output_dir>/<title-slug>.pdf). This goes far beyond the minimal schema titles and gives the agent actionable guidance.

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 opens with a clear, specific statement: 'Convert Markdown text to a PDF and return metadata plus the inline file.' It names the action (convert), the resource (Markdown text), and the output (PDF plus metadata), making the tool's purpose unmistakable. Though it doesn't explicitly contrast with sibling tools, the name and description already disambiguate from validate_spec and create_pdf.

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?

There is no guidance on when to use this tool versus alternatives like create_pdf or validate_spec. No prerequisites, exclusions, or decision heuristics are provided. The description focuses entirely on parameter meanings and defaults, leaving the agent to infer appropriate usage context.

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 the full burden and does well: it states the tool does not render, explains that strict mode resolves through the engine, reports flowable count and engine warnings, and requires reportlab. This is meaningful behavioral context beyond the bare schema.

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 compact and front-loaded: the core purpose appears in the first line, and the strict-mode behavior is a clean, short addendum. Every sentence earns its place and there is no filler or repetition of schema data.

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 output schema exists, return-value details do not need to be repeated. The description covers the tool's main behavior, the strict-mode difference, and the reportlab prerequisite. Minor gaps remain, such as what happens if reportlab is absent, but overall an agent has enough to invoke it 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?

Schema description coverage is 0%, so the description must compensate. It adds real semantics to the strict parameter, including what strict resolution does and its dependency. However, it gives no additional detail about the structure or expected shape of the spec object, which is undocumented in the schema as 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 names a specific verb ('Validate'), a specific resource ('document spec'), and an explicit exclusion ('without rendering it'). This clearly separates it from the sibling tools create_pdf and from_markdown, so an agent can distinguish it without inspecting their schemas.

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 conveys when to use the tool: to validate a spec rather than render it. It also clarifies the optional strict mode and its dependency on reportlab. However, it does not explicitly name create_pdf or from_markdown as alternatives or state when not to use them, so it misses the top tier of routing guidance.

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