Arne Kellmann Consulting

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

Annotations already mark readOnlyHint=true and destructiveHint=false. The description reinforces this with 'Read' and adds that it does not book or send anything. This is useful but largely aligned with existing annotations; no additional behavior such as auth or rate limits is disclosed.

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 concise sentences front-load the core purpose and add one usage clarification. No redundant wording.

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 read-only listing tool with an output schema, the description covers the resource content and usage intent. The only missing piece is an explanation of the language parameter, but the schema enum makes acceptable values 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 has one optional parameter 'language' with enum and default, but no description. The tool description does not mention or explain the language parameter or its effect, and with 0% schema description coverage, the description fails to compensate.

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 'Read' and specifies the exact resources: consulting services, pricing policy, and contact URL. It also clarifies what the tool does not do ('does not book or send anything'), which distinguishes it from transactional tools and from read_document/search_docs siblings.

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 an explicit use case: 'Use to assess engagement fit.' It also warns that it does not book or send anything, which tells the agent not to use it for actions. However, it does not mention the sibling tools or contrast with them.

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 and destructiveHint=false, covering the safety profile. The description adds the context that the tool reads from published site documentation, which is useful, but it does not mention behaviors like 404 handling, frontmatter handling, or whether the returned content is raw markdown or rendered HTML. Still, for a read-only retrieval tool the annotation coverage means the burden is lower.

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 one compact sentence with concrete examples. It is front-loaded with the action and target, and every word earns its place. No redundancy or filler.

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 has only one parameter, a clear output schema exists to explain return values, and annotations already declare read-only safety. Given this simplicity, the description is sufficient for an agent to invoke it correctly. The examples and path-based semantics complete the picture.

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%, so the description fully explains the 'path' parameter's meaning: it should be a markdown path like /index.md, /pricing.md, or /auth.md. However, the description does not specify path constraints beyond the schema's maxLength, and does not explain what happens for invalid or non-markdown paths. Baseline 3 is appropriate because the description compensates for the missing schema 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?

The description clearly states the tool's function: reading a published site markdown document by path. It provides concrete examples like /index.md, /pricing.md and /auth.md, which immediately disambiguate it from sibling tools like list_services and search_docs. The verb 'read' plus the resource ('published site markdown document') is specific and actionable.

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 implies the tool is for retrieving markdown content given a path, and the examples strongly suggest when to use it. It does not explicitly discuss when not to use it or recommend an alternative, but in context of siblings (list_services, search_docs), the use case is clear enough for an agent.

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 mark readOnlyHint=true and destructiveHint=false; the description adds meaningful context by disclosing the return shape (source URLs and excerpts) and what the tool will not do ('no generated advice'). This is especially useful for an AI agent choosing between tools in a documentation 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 front-loads the action and resource, then adds valuable return information and a caveat. Every clause earns its place with no redundant wording.

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 annotations covering the safety profile, the description sufficiently covers the tool's core purpose, return content, and key limitation. It does not mention the language parameter, but that is adequately documented in the input schema.

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%, so the description needs to compensate. It partially does by implying that 'query' is a keyword string ('Search ... using keywords'), but it does not mention the 'language' parameter at all. The parameter names and enum/default in the schema help, but the description does not carry enough weight for the low coverage.

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 ('Search'), identifies the resource ('published site documentation'), and clarifies the retrieval behavior ('Returns source URLs and excerpts; no generated advice'). This clearly differentiates it from sibling tools like read_document (likely reading a specific doc) and list_services (listing services).

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 clearly establishes this as the keyword-search entry point for documentation, so an agent knows when to invoke it. However, it does not explicitly name alternatives or state when to use read_document or list_services instead.

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