graph_schema

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect disclosure. The description adds that it returns specific schema categories (nodes, edges, tags, rules), which goes beyond annotations. It doesn't mention error behavior or rate limits, but for a read-only metadata tool, this is reasonably transparent.

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 compact sentence that front-loads the tool's output and purpose. No wasted words, and the 'don't guess' imperative adds actionable value in the second clause. Perfectly concise and well-structured.

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?

While annotations cover safety, the description omits key parameter behaviors (max_chars truncation, response_format verbosity) and doesn't describe the output structure (though no output schema exists). The tool is simple enough that an agent might infer some things, but the lack of parameter documentation for a 0% coverage schema makes it incomplete.

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. It only implicitly explains the 'section' parameter by listing its enum values (node types, edges, tags, rules). 'max_chars' and 'response_format' are left completely unexplained. This is a significant gap given the coverage is zero.

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 specifies exactly what the tool returns ('node types, edges, tags, diagnostic rules') and frames it as the authoritative schema source ('don't guess, verify with this tool'). This clearly distinguishes it from sibling tools like 'query' or 'find' which operate on data rather than 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 instruction 'don't guess the schema; verify with this tool' provides a clear directive on when to use it (whenever schema knowledge is needed) and implies it is the correct alternative to guessing or using other tools for schema discovery. It doesn't explicitly exclude other tools, but the context is strong enough.

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