spring_reference

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

With no annotations, the description carries the full burden and does so: it discloses offline resolution when the index is cached, that max_tokens truncates at a line boundary and sets a 'truncated' flag, that narrowing keeps only the matching heading section plus title/description, and that failure returns {"error", "suggestion", "candidates"}. These are behavioral traits well beyond a bare read.

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?

Front-loaded with the core purpose and organized by parameter, with each paragraph earning its place. It is somewhat long and mildly discursive ('no request is wasted guessing a URL and getting a 404'), but the length is justified by the amount of non-obvious behavior being documented.

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?

No output schema and no annotations, so the description must cover everything, and it does: purpose, parameter semantics, resolution fallback, truncation, and failure payload. An agent has enough to call the tool correctly and interpret both success and error results.

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 must compensate, and it does for every parameter: section/subsection resolution semantics, version ('e.g. "4.1"', omitted reads latest), and max_tokens including the estimation formula (len(text)//4) and the resulting 'truncated' flag. This adds far more meaning than the bare schema types.

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 Spring Boot reference section or subsection as clean markdown') and explains exactly what 'section'/'subsection' resolve against. It also positions itself relative to java_docs by saying the narrowing behavior is 'the same behaviour as java_docs(topic=...)', letting an agent distinguish it from siblings without opening both schemas.

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 concrete usage context: valid resolution examples ('web', 'data'+'sql', 'how-to'+'actuator'), behavior when subsection is not its own page, and the note fallback when nothing matches. However, it never states when to reach for this tool over spring_guides, spring_search_concepts, or spring_search_concepts for discovering section names, so explicit alternatives/exclusions are absent.

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