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

Annotations are minimal (readOnlyHint=false, idempotentHint=false), so the description carries most behavioral disclosure. It adds the 20 MB limit, plan/billing rule, output format, and 'not kept' retention behavior; it stops short of describing error cases or URL lifetime, which are secondary.

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 dense sentences lead with the core action and result, then pack constraints, plan requirements, and source modes without redundancy. Every clause adds useful information.

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 an 8-parameter tool with no output schema, the description covers formats, size, result, billing, source exclusivity, and retention. It could add URL expiry or failure behavior, but nothing essential for selecting and invoking the tool is missing.

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 parameters are already documented. The description adds the crucial mutual-exclusion constraint that exactly one of render_id, path, or file_base64 must be supplied and that file_base64 pairs with file_name, which the schema alone does not convey.

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 opening sentence states a specific verb (Converts) and resource (office document to PDF) and returns a download URL, which distinguishes it from render-oriented siblings. Listing supported formats further narrows the tool's purpose.

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?

It clearly describes the three source modes and states 'Pass exactly one source', giving an agent the key precondition. It does not explicitly name sibling alternatives or say when not to use them, but the render_id option ties it naturally to the render workflow.

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 the safe-read profile is covered. The description adds that the tool returns status, download URL, and error, which is useful, but it does not disclose behaviors like not-found handling, URL expiration, or auth requirements. With annotations present, the bar is lower, and this meets it 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 a single concise sentence that front-loads the key output fields and includes the id format. Every word contributes value with no 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?

For a simple single-parameter read tool with no output schema, the description adequately covers what the tool returns and what the id should look like. It could add more about error/not-found behavior, but the core information an agent needs to call it correctly is present.

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 0% and the schema only says id is a string. The description compensates by specifying the expected id format (rnd_…) and clarifying that it is a render id, which is meaningful beyond the raw 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?

The description identifies the resource (a render), the key identifier format (rnd_…), and the returned information (status, download URL, error). While it is a noun phrase rather than an explicit verb phrase, the title 'Get a render' supplies the verb, and the content clearly separates this read tool from siblings like render (creation) and list_templates.

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: call this when you have a render id and need its status or download URL. There is no explicit when-not-to-use guidance or mention of alternatives, though the sibling list makes it inferable that render creates and convert_to_pdf converts.

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 readOnlyHint annotation already covers the safety profile (read-only). The description adds value by disclosing that the tool returns both the JSON schema and the sample data, which is behavioral information beyond the annotation. It does not contradict any annotation.

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 consists of two concise sentences. The first states the core function and output, the second gives a clear usage instruction. Every sentence serves a purpose with no 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?

For a simple tool with one well-documented parameter and a read-only annotation, the description is complete: it explains what the tool returns (schema and sample data) and how to use it (to build data for render). No essential information is missing for an agent to call 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?

The input schema already documents the only parameter 'template' with a clear description ('Template slug or tpl_ id'), achieving 100% coverage. The tool description does not add any extra detail about the parameter beyond what the schema provides, so the baseline 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 states a specific verb and resource: it returns the JSON Schema of the expected 'data' object for a template, plus sample data. This clearly distinguishes it from siblings like 'render' (which processes data) and 'validate_template' (which checks correctness).

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 explicitly tells the agent when to use it: 'Use it to build the data for render.' This gives clear context for the use case. However, it does not mention when not to use it or alternatives, leaving a small gap.

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 annotation readOnlyHint=true already indicates the operation is read-only, so the description does not need to repeat that. The description adds context about the returned fields (kind mapping to file types), which is mildly useful but does not disclose behaviors like pagination, ordering, or rate limits. It adds some value beyond annotations but not rich behavioral context.

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 sentence that directly states the purpose and scope. It front-loads the core action and provides essential field details without any fluff. Every word contributes value, making it highly concise and well-structured.

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 list operation with 4 optional parameters and no output schema, the description gives a sense of what is returned but omits key contextual details such as pagination, sorting, filtering behavior, or any limitations (e.g., max results). While the tool is simple, more specifics would help an agent know what to expect when calling it. It is adequate but has clear 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 description coverage is only 25% (only 'q' has a description). The description adds meaning for the 'kind' parameter by mapping values to file types (docx for Word, pptx for PowerPoint), which goes beyond the schema enum. However, it does not explain 'tag', 'engine', or clarify the 'q' parameter beyond its schema description. With low coverage, the description only partially compensates, leaving most parameters semantically thin.

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 (list) and resource (templates) with specific details about returned fields (slug, kind, engine, published version). It scopes to the workspace of the API key, which adds clarity. However, it does not explicitly differentiate from sibling tools like get_template_schema or render, so it misses the 'distinguishes from siblings' criterion for 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?

The description provides no guidance on when to use this tool versus alternatives. It does not mention when not to use it or point to other tools for specific use cases. The only context is the workspace scoping, which is more about data scope than usage selection. This is essentially no usage 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 only state readOnlyHint=false and idempotentHint=false, leaving the description to carry behavioral context. The description adds useful transparency by noting that live keys consume units, test keys add a watermark, and the tool returns a download URL. It stops short of explaining side effects like resource creation or quota impact, but it adds meaningful value beyond the annotations.

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 core operation and output, and wastes no words. It packs the essential purpose, input types, output formats, return value, and billing behavior into a compact, scannable form.

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?

This is a complex 8-parameter tool with no output schema, so the description needs to cover return values and operational call requirements. It explains the download URL and main rendering paths, but it does not state whether a template or html is required, how filename behaves, or how asynchronous renders are retrieved. These gaps leave an agent with some uncertainty before invoking the 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?

Schema description coverage is 75%, so the schema already handles most parameter documentation. The tool description clarifies high-level input modes (template+data vs raw HTML) and output format categories, but it does not add detail for undocumented parameters like data or filename. It is neither harmful nor highly compensatory.

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 a specific verb and resource: it renders templates or raw HTML into PDFs, images, DOCX, or PPTX, and returns a download URL. It does not explicitly differentiate itself from siblings like get_render or convert_to_pdf, but the output and rendering scope make the core purpose evident.

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 billing-related context (live keys consume units, test keys render with a watermark) but gives no guidance on when to use this tool instead of alternatives such as convert_to_pdf, get_render, or validate_template. It lacks explicit exclusions, prerequisites, or scenario-based routing.

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 goes well beyond the readOnlyHint=true annotation: it states that no rendering occurs, that slug-mode checks the same version a render would, that html-mode compiles offline, that warnings preserve ok true, and that Word/PowerPoint findings include document part and paragraph. This is rich, actionable behavioral detail.

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 but not bloated: five sentences, each earning its place. The first sentence front-loads the core purpose and cost/rendering behavior, followed by mode details, warning semantics, and output location details. No filler or 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?

For a read-only validation tool with no output schema, the description covers most critical aspects: modes, error categories, warning behavior, and output granularity. It falls slightly short by not explicitly stating the required combination of template or html+engine (the schema lists no required fields), and by leaving the overall response structure mostly implicit aside from the ok flag.

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 already documents data, html, engine, and template with 75% coverage. The description adds meaningful semantics: template can be a slug or tpl_ id, slug mode validates the published-or-latest version, html mode requires engine and compiles offline, and data is validated against the stored JSON Schema. This supplements the schema effectively.

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 'Checks a template with data without rendering; free,' naming a specific action, resource, and the key differentiator from rendering. It further clarifies two distinct invocation modes (slug vs html+engine), making the purpose unmistakable.

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?

It clearly implies usage: validate before rendering, avoid rendering costs, and choose between a template slug or html+engine mode. However, it never explicitly states that exactly one of these modes is required, nor does it discuss when not to use it relative to sibling tools like get_template_schema.

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