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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely non-obvious behavior: it resolves the source from the project's node_modules when installed, otherwise falls back to the latest npm version, and it states the return is a declaration including JSDoc. The version-resolution fallback is exactly the kind of context an agent cannot get from 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?

Two sentences, front-loaded with what the tool returns before the usage hint. The trailing list of five example symbols is slightly long but functions as concrete grounding rather than filler. No redundant restatement of the 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?

There is no output schema, and the description compensates by saying exactly what is returned (a TypeScript declaration with JSDoc) and where it is sourced from (local node_modules or npm latest). For a two-parameter read-only lookup with full schema coverage, nothing an agent needs in order to call it correctly 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 both `symbol` and `package` are already documented, including the @qodalis/cli-core default and the "cli-core" shorthand. The description reinforces usage with concrete symbol examples (ICliCommandProcessor, ICliExecutionContext, ...) but adds no syntax or format detail beyond the schema. Baseline 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?

The description names a specific verb+resource: retrieving the TypeScript declaration (with JSDoc) for a named symbol from @qodalis packages. It enumerates the symbol kinds (interface, type, class, function, enum, constant) and gives concrete examples, so an agent knows exactly what comes back. It does not explicitly contrast itself with qcli_docs_search/qcli_docs_read, which is the main remaining ambiguity.

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?

"Use it for exact member names and signatures" gives a use condition, which is more than nothing. But there is no exclusion or routing rule against the sibling docs tools — an agent must infer that this is for precise signature lookup while qcli_docs_search is for prose/narrative discovery.

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 and openWorldHint, so the bar is lower, and the description still adds real behavioral detail: the payload is markdown with code samples, and a non-matching topic does not error — it returns a topic listing instead. That fallback behavior is the kind of thing an agent can't infer from annotations or 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?

Three tight sentences: what it returns, how to address a topic, and the fallback. The most important information (what you get back) is front-loaded and no sentence 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?

For a single-required-parameter read tool with no output schema, the description covers the return format, the three addressing modes, and the failure path. Nothing an agent needs in order to call it correctly 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 coverage is 100%, so the baseline is 3, and the description adds value on top by specifying that matching is case-insensitive and that a bare section name returns the entire section — semantics not present in the schema's one-line parameter 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?

States a specific verb and resource: 'Read a topic of the Qodalis CLI plugin-development guide in full (markdown with code samples).' The 'in full' framing implicitly separates it from qcli_docs_search, but the search sibling is never named, so differentiation is left to inference rather than explicit.

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?

Gives rich guidance on HOW to form the argument (case-insensitive heading, 'Section › Topic', or section name) and what happens on a miss, but never says when to pick this over qcli_docs_search — e.g. 'use search first when you don't know the heading.' Usage is implied, not stated relative to alternatives.

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 cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower, but the description still earns credit by disclosing the return shape: 'Section › Topic' entries with a summary and an excerpt. With no output schema, this is the main disclosure the agent needs; ranking criteria and excerpt length are left implicit.

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 sentences, front-loaded with what is searched, followed by the return format and the follow-up tool. Nothing is padded or 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?

For a two-parameter read-only search with no output schema, the description supplies the corpus, the result shape, and the next step, which is sufficient to invoke it correctly. The only missing piece is the boundary against qcli_api.

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%, so both parameters (query, limit) are already documented in the schema. The description adds no query syntax or matching-behavior detail beyond that baseline, so a 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?

A specific verb (Search) plus a clearly scoped resource (the Qodalis CLI plugin-development guide, enumerated as web plugins, server plugins, recipes). It is directly distinguishable from the qcli_docs_read sibling, which it names.

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?

Explicitly routes the agent: search here to get best-matching topics, then 'read one in full with qcli_docs_read'. That covers the search-then-read workflow, but it never contrasts this with qcli_api, which an agent could plausibly choose for reference lookups, so the sibling differentiation is incomplete.

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=false, openWorldHint=true, idempotentHint=false, and this description adds substantial context beyond them: it runs an npx generator (network fetch), writes to packages/plugins/<name> or a standalone qodalis-cli-<name> project, and installs dependencies as a side effect. It also states what is returned (created files and next steps), which is important since no output schema exists.

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 dense sentences, front-loaded with the action and the generator, followed by location behavior and return value. Every sentence carries new information with no repetition of the title or 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?

It covers what is created, where it lands, that dependencies are installed, and what is returned, which is sufficient given full schema coverage and no output schema. It omits edge-case behavior such as what happens when the target plugin directory already exists, which matters given idempotentHint=false.

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 name, directory, description, and processorName are each documented in the schema itself. The description adds no parameter-level syntax or defaults beyond that, so the 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 first sentence names a specific verb (create), the exact resource (web CLI plugin), the concrete generator used (@qodalis/create-cli-plugin via npx), and enumerates what the scaffold contains (processor, module, build config, tests). That is far more specific than the sibling docs/api tools, so an agent can distinguish it without opening a schema.

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 context for when the tool applies and even explains the two different target locations depending on whether it runs inside a web-cli checkout. It does not state exclusions or explicitly redirect to any sibling tool, so it stops short of full alternative routing.

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