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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds crucial behavior: 'Uses metered access when findings exist.' This is a meaningful addition beyond the annotations, as it signals a cost/limit consideration. A small deduction because it doesn't specify what happens to the results or if there's any deprecation-specific data returned.

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 sentences, each earning its place: purpose, usage pattern, and caveat. It's dense but not bloated. Losing a point for front-loading critical info (purpose) well but the metering note feels slightly secondary, though still relevant.

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 read-only scanning tool with clear annotations and an output schema, the description is quite complete. It explains the tool's niche (deprecation scanning) and distinguishes from siblings. The only minor gap is not explaining what 'metered access' means for the user, but the sibling reference and annotations cover most context needs.

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% and the schema already describes 'Optional service filter' and 'Optional endpoint paths to check'. However, the description adds important context about how to use the filters ('Omit filters...', 'pass service to limit one API', 'add endpoints to check selected paths'). The baseline for 100% coverage is 3, and the description earns an extra point for giving semantic meaning to the parameters.

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 ('Scan') and names the resource ('publisher specifications') and subject matter ('deprecated endpoints or parameters, sunset dates, replacement operations'). It clearly differentiates itself from siblings by explicitly pointing to `factreason_api_breaking_changes` for broader changes.

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?

It provides clear when-to-use guidance: 'Omit filters for the catalogue-wide view, pass service to limit one API, and add endpoints to check selected paths.' It also references the alternative sibling tool by name, which addresses the 'vs alternatives' criterion directly.

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