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

With no annotations, the description carries the full burden of behavioral disclosure. It conveys a read-only 'get' operation and explains the reverse-lookup behavior, but it does not disclose details like pagination behavior, ordering, or the effect of max_results beyond its default. For a read tool, this is adequate but minimal; it lacks richer context about what happens with large result sets or how output is structured (though an 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?

The description is concise and front-loaded with the core purpose, followed by an Args block that documents each parameter. The format is slightly awkward due to the indented code-block style, but every sentence adds value. It is not overly verbose, and the structure is clear.

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 lookup tool with two parameters, an output schema, and a clear scope (reverse lookup), the description provides enough information to invoke it correctly. It does not include usage examples or explicit tie-ins to sibling tools, but given the tool's simplicity and the presence of an output schema, it is largely complete. The absence of read-only annotation is compensated by the 'get' verb.

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 explicitly explains spec_number as 'Specification number to find dependents of' and max_results as 'Maximum results (default: 50)', adding meaningful context beyond the bare schema titles 'Spec Number' and 'Max Results'. This is sufficient parameter-level guidance, though it could be more detailed about the semantics of max_results (e.g., pagination vs. limit).

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 purpose: 'Get all specifications that reference a given spec (reverse lookup).' It uses a specific verb ('get'), identifies the resource ('specifications that reference a given spec'), and adds the crucial scope 'reverse lookup' which distinguishes it from sibling tools like get_spec_references (which likely does forward lookup). This is a specific, non-tautological statement.

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 when to use the tool via the 'reverse lookup' phrase, signaling this is the tool for finding dependents rather than forward references. However, it does not explicitly name alternative tools or state when not to use it. The context is clear enough for an agent to decide, but it stops short of explicit exclusion or alternative comparison.

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