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

With no annotations, the description carries the load and does well: it discloses filesystem writes, where outputs land (out_dir under the current working folder), what stage 'all' additionally produces (PNG, .bpmn, Camunda import check), and the full response shape (ok, errors, warnings, files, log). It does not say whether existing files are overwritten or what permissions/setup are needed, which is the remaining behavioral gap for a write 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?

One lead sentence followed by terse per-parameter lines and a returns line, with no filler. The most decision-critical constraint (draft vs. approved stages) is stated inline where the agent will look for it.

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 five-parameter tool with an unconstrained nested spec object and no output schema, the description supplies the return fields and behavioral constraints, and correctly offloads spec structure to bpmn_spec_guide. It is nearly complete, but the absence of any mention of bpmn_setup_check leaves the workflow entry point ambiguous.

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 every one of the five parameters is explained beyond its name: spec is the JSON object defined in bpmn_spec_guide, name is the extensionless file name with an allowed character set, out_dir is resolved under the current working folder, stage enumerates its two values with intent, and preview is defined separately for each stage.

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 names concrete verbs and resource: 'Lay out and check a diagram, and write the files' — an agent knows exactly what comes out. It also differentiates itself from bpmn_spec_guide by delegating spec format there ('see bpmn_spec_guide').

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 stage parameter carries explicit when-to-use guidance: 'svg' = 'use while drafting', 'all' = 'use only after the user approved the drawing', and the return line instructs 'fix every one and build again'. The one gap is that the sibling bpmn_setup_check (a likely prerequisite) is never mentioned, so the ordering relative to it must be inferred.

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 present, the description carries the full burden, and it does disclose that the tool writes nothing and returns plain-language findings — useful safety and output-shape context. It does not say what specific checks are performed, what prerequisite tooling is inspected, or whether it suggests remediation when something is missing.

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 short and front-loaded: the core purpose and the non-mutating guarantee come first, followed by the usage triggers. The line breaks make it slightly fragmentary, but every sentence carries information and none is wasted.

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 zero-parameter diagnostic with no output schema and no annotations, the agent has what it needs to decide to call it and to expect plain-language findings rather than structured data. The only gap is detail on what is actually verified and whether a failure implies a concrete fix.

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. The baseline of 4 applies, and the description correctly implies no inputs are 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?

The description states a concrete verb and target: verifying that the machine is able to draw diagrams. 'Writes nothing' further scopes it as a non-mutating preflight check, which distinguishes it from bpmn_build. It stops short of naming the sibling tools explicitly, so it isn't maximally differentiated.

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?

Two clear triggering conditions are given: when a user asks to set up, and when a build fails with a browser error. That is real when-to-use guidance tied to observable situations. There is no explicit 'do not use when' or direct pointer to bpmn_build / bpmn_spec_guide as the next step.

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 must carry the behavioral load, and for a zero-parameter reference tool it does: it makes clear this returns static guidance content rather than mutating or querying anything. It omits any statement about statelessness/caching or response size, which are the only remaining unknowns.

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 short sentences, zero filler, and the content summary is front-loaded ahead of the call-timing instruction. Nothing could be cut without losing 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?

With an output schema present and no parameters, the description need not explain return values, and it correctly focuses on what the guide contains and when to read it. The only thin spot is that it doesn't say whether to re-read it after a check fails or how it relates to bpmn_setup_check.

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 no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a no-argument call by giving no input requirements.

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 action (return) and concrete content (diagram spec format, layout rules, per-error fixes), so an agent knows exactly what this tool yields. It implicitly separates itself from bpmn_build by telling the agent to read this first, but never contrasts with bpmn_setup_check, the other sibling in the same family.

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?

"Read this before the first bpmn_build call" gives an explicit trigger point for invoking the tool. The mention of "fixes for each check error" also implies a second use case after a failing check, though neither exclusion nor a re-read rule is stated outright.

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