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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about what files get written or overwritten, what happens when a capability of the same name exists (the force flag hints at overwrite but is never explained), whether dryRun defaults to false, or that this mutates the project on disk.

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, front-loaded with the action and scope, with the spec clarification tacked on usefully. Efficient, though the second sentence's pronoun ('spec') is slightly clipped.

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?

An output schema exists so return values needn't be described, and required params are named. But for a file-mutating tool with zero annotations, an undocumented force flag, and an unexplained dryRun option, the definition is thinner than the tool's complexity warrants.

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?

Only 'spec' gets meaning beyond the schema ('the parsed JSON spec object', implying the caller must parse the file rather than pass a path), and 'kind' is just restated. With 60% schema coverage, the undocumented 'force' and 'dryRun' flags — both behaviorally significant for a mutating tool — are left entirely unexplained in both schema and description.

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?

Names a specific verb and resource ('Add a tool, prompt, or resource') scoped to 'an existing mcpgen-generated project', which implicitly distinguishes it from mcpgen_new (new project) and mcpgen_schema/check. It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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 phrase 'to an existing mcpgen-generated project' implies the prerequisite and hints that project creation belongs to mcpgen_new, but there is no explicit when-to-use/when-not guidance, no mention of what to do if the capability already exists, and no routing to mcpgen_check for validation.

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 supplied, the description carries the burden, and it does disclose the outcome model: ok=true means green, stages enumerates per-stage status, and error.fix gives the first failure at file:line. That is genuinely useful behavioral context. However, it omits side effects (does the pipeline write anything to disk?), expected runtime, and whether it is safe to run repeatedly — important for a tool whose name suggests a full pipeline.

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?

A single dense sentence with the outcome semantics front-loaded and no filler. It could be split for readability, but nothing is redundant.

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?

Because an output schema exists and the input schema is fully described, the description only needs to frame intent and outcome, which it does. Minor gaps remain around side effects and interaction between the description and the optional stages (inspector/conformance), but an agent has enough 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?

Schema description coverage is 100%, so all four parameters (dir, inspector, timeoutSec, conformance) and their defaults are already documented. The description adds no parameter-level meaning beyond the prose, so the baseline of 3 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?

States a specific verb and resource ("Run the mcpgen verification pipeline") and ties it to the CLI command it wraps (`mcpgen check`), which makes the tool's job immediately identifiable. It doesn't explicitly contrast itself with siblings like `mcpgen_add` or `mcpgen_schema`, but the verify-vs-scaffold distinction is clear from the wording.

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 only implied: an agent can infer it should call this to check a project's health, but there is no explicit when-to-use/when-not or reference to the sibling tools. No prerequisites (e.g. project must already be generated) are stated.

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. It usefully discloses that the tool writes files unless dryRun and runs a validation pipeline unless noCheck, but it omits that generation into an existing non-empty directory fails without force, does not say whether existing files can be overwritten, and gives no sense of reversibility or failure behavior.

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, front-loaded with the core action, and no wasted wording. The dryRun and noCheck behavior is stated compactly.

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 14-parameter generator that writes files and runs validation, yet the description explains only two boolean side effects. The output schema covers return values, but the description does not prepare an agent for directory conflicts, force semantics, transport/module choices, or the relationship between tools, prompts, and resources.

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 the baseline is 3. The description adds a little meaning for dryRun and noCheck by explaining their effect, but says nothing about the other 12 parameters, including force, dir, transport, or feature selection.

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: generate a new Go MCP server project, with the CLI equivalent `mcpgen new`. It distinguishes itself reasonably from `mcpgen_add`, `mcpgen_check`, and `mcpgen_schema` by the word 'new', though it never explicitly contrasts them.

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 only usage guidance is behavioral: writes files unless dryRun and runs validation unless noCheck. There is no guidance on when to use this tool instead of `mcpgen_add` or `mcpgen_check`, no prerequisite for existing directories, and no mention that `force` is needed for non-empty output.

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?

No annotations are supplied, so the description carries the full burden. It usefully discloses what the returned payload contains (commands, flags, exit codes, JSON envelope, JSON Schema), which is effectively a return-value summary, but leaves the verb 'Emit' ambiguous: it does not say whether output goes to stdout or is written to a file, nor whether the call has side effects or is purely read-only.

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?

A single front-loaded sentence with a compact colon-delimited list of contents; nearly every clause adds information. The trailing parenthetical '(mcpgen schema)' restates the tool name and is mildly redundant.

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 no parameters and no output schema, the description does the right thing by enumerating the returned document's sections, but it stops short of describing the transport/format of the emitted output or its size, which is the main thing an agent still needs to know before calling.

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 the baseline is 4; there is nothing for the description to disambiguate. It correctly implies the call is parameterless by describing a fixed document rather than configurable output.

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?

Uses a specific verb ('Emit') with a concrete resource ('the mcpgen schema document') and enumerates its contents: commands, flags, exit codes, the JSON envelope, and the mcpgen.json JSON Schema. This clearly separates it from the sibling mutation/validation tools (mcpgen_add, mcpgen_check, mcpgen_new), though it never names them explicitly.

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 when-to-use guidance, no statement of prerequisites, and no reference to alternatives such as mcpgen_check. The agent must infer from the purpose alone that this is the self-description/discovery call rather than a validation or scaffolding call.

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