pdfzen

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

Annotations already declare readOnlyHint=true, and the description adds extra context: 'Free, no payment, no auth required,' which directly informs the agent about auth requirements and cost. It also details the return payload (HTML, CSS, sampleData, pageOptions), going beyond the minimal safety profile.

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: the first states the core action, the second gives usage guidance, and the third adds access information. No wasted words, front-loaded with the primary purpose.

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 tool is simple with one parameter and no output schema. The description fully compensates by enumerating the returned components and explaining exactly when and why to use it, making the tool self-contained and clear.

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 schema covers the single parameter 'slug' 100% with examples and a pointer to list_starters for discovery. The description adds no further parameter-level detail beyond saying 'by slug', so the baseline 3 for high schema coverage 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?

The description uses a specific verb ('Fetch') and resource ('full HTML body, CSS, sampleData, and pageOptions for one starter template by slug'), clearly distinguishing it from siblings. It explicitly mentions the use case of understanding data shape before calling render_template_to_pdf, which separates it from rendering 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 description provides explicit usage context: 'Use this when you need to understand the exact shape of `data` the template expects before calling render_template_to_pdf, or when you want to fork a starter into custom HTML.' It lacks an explicit 'when not to use' but the alternatives are implied through sibling mentions and the focused use cases.

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 declare readOnlyHint=true, so no contradiction; the description adds valuable behavioral context beyond that: 'Free, no payment, no auth required' and the exact return array structure. While it doesn't disclose rate limits or pagination, for a read-only list endpoint with a short fixed count (45), this is sufficient additional 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?

The description is three sentences but each serves a distinct purpose: what the tool lists, what it returns, and how to use it in the broader workflow. It is front-loaded with the main purpose and contains no filler or repetition of the tool name.

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?

Even without an output schema, the description explicitly states the return array shape, which is the key missing structured information. Combined with the read-only annotation and the explicit usage sequence involving sibling tools, the description is fully complete for a simple no-parameter list operation.

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 has zero parameters and the input schema is empty (100% schema description coverage), so the baseline for no parameters is 4. The description compensates by naming the returned fields ({ slug, name, description, icon, pageOptions, fonts, dataKeys }), which indirectly clarifies that no input is needed because the tool simply enumerates a fixed set.

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 specific verb and resource: 'List pdfzen's 45 public starter templates', enumerating example categories to make the scope concrete. It clearly distinguishes itself from sibling tools (get_starter, render_html_to_pdf, render_template_to_pdf) by focusing on listing available templates rather than fetching or rendering.

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 when-to-use guidance is provided: 'Call this first to discover what fits the user request' and then a recommended sequence ('optionally call get_starter... then call render_template_to_pdf'). This directly addresses how to use the tool relative to its siblings, satisfying the highest bar for usage guidelines.

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?

The description discloses significant behavioral context beyond annotations: the tool returns a ready-to-execute HTTP request rather than rendering in-band ('pdfzen renders are executed over HTTP, not streamed in-band over MCP'), includes pricing and endpoint details ('$0.006 USDC on Base, no API key' vs 'pdfzen API key'), and mentions HTML validation. This substantially enriches the annotation readOnlyHint=false and openWorldHint=true.

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 information-dense yet concise, front-loaded with purpose and immediately followed by usage guidance and key behavioral details. Every sentence earns its place, covering purpose, alternatives, cost, endpoints, auth, and the bridge nature without fluff.

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 exists, so the description carries the burden of explaining return value, which it does clearly ('returns the exact, ready-to-execute HTTP request'). It also covers the two execution environments, pricing, auth differences, and validation, making it complete for a tool of this 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 coverage is 100% with detailed descriptions for all four parameters, so the description need not compensate. The description does mention Handlebars-flavoured HTML and the returned HTTP request but adds little to parameter-specific meaning beyond what the schema already provides. 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's purpose: 'Prepare a paid PDF render from arbitrary Handlebars-flavoured HTML.' It distinguishes itself from siblings by explicitly saying 'Use only when no starter fits' and 'Prefer render_template_to_pdf when a starter matches.' The verb 'prepare' and resource 'paid PDF render' are specific.

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 on when to use: 'Use only when no starter fits (one-off layouts, custom branding).' It also names the alternative: 'Prefer render_template_to_pdf when a starter matches.' This is a clear when/when-not with an explicit alternative.

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 (readOnlyHint=false, openWorldHint=true), the description discloses the paid nature ($0.006 USDC), two HTTP endpoint variants, the fact that renders are executed out-of-band, and the merge-on-top behavior with sampleData. This is rich, actionable behavioral detail that goes well beyond what annotations provide.

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 dense yet efficient—each sentence adds substantive value, covering purpose, pricing, the HTTP bridge, and merge semantics. It is front-loaded with the core purpose and avoids any filler 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?

Even without an output schema, the description fully explains what the tool returns (an exact HTTP request), how it's executed, and the pricing model. It also references sibling tools for template discovery, making the tool completely usable in context.

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?

Input schema descriptions already cover all 3 parameters at 100%, so the baseline is 3. The description adds meaningful context by explaining that `data` merges on top of sampleData and that partial payloads inherit demo defaults, which is not present in the schema. This extra semantic value justifies a 4.

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 'Prepares a paid PDF render from one of the 45 starter templates' and explains it returns a ready-to-execute HTTP request. This specific verb and resource scope distinguish it from sibling tools like render_html_to_pdf, which handles arbitrary HTML, and get_starter/list_starters, which are informational.

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 usage context: it is a bridge for executing PDF renders over HTTP, and parameter descriptions advise calling list_starters or get_starter when unsure. However, it does not explicitly name the alternative render_html_to_pdf for non-template rendering, so it falls just short of providing explicit when/when-not guidance.

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