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

With no annotations provided, the description carries the full burden and fully delivers. It states the tool finds pages rather than computes, ranks with 'New Zealand specific pages first', and describes the returned structure: 'ranked list, each with title, url, type ..., category and description.' It also explicitly names limitations, making the behavior transparent beyond the tool name.

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 organized into a clear one-sentence summary, usage context, Args, and Returns sections. It front-loads the core behavior, then layers in usage, ranking, and output detail. Every sentence earns its place by providing routing, limitation, or parameter guidance, with no filler or repetition.

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 two-parameter search tool with no output schema, the description is complete. It covers when to use it, when not to use it, ranking behavior, parameter details, and the exact return fields, including the instruction to 'Link the url when recommending a page.' Nothing needed for correct invocation is missing.

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 0%, so the description is the only source of parameter meaning. It explains query as 'what the user wants to work out, in plain language' and gives a concrete example: natural questions work better than keywords. It also clarifies limit: 'How many results to return, 1 to 20. Default 5.' This adds substantial value over the bare schema.

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 opens with a specific verb and resource: 'Search all 2,377 Calculate.co.nz calculators, guides and datasets by topic.' It clearly differentiates itself from siblings by stating that only a handful of the site's tools have their own MCP tool and that this one 'searches EVERYTHING' and 'returns the pages that match.' An agent can immediately tell this is a broad search tool rather than a dedicated calculator.

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 gives explicit when-to-use instructions: 'Use for ANY question of the form ...' and 'whenever a New Zealand calculation is asked about and no specific tool above fits.' It also provides exclusions: 'it does not compute' and 'cannot answer non-New Zealand questions about foreign tax or benefit systems.' This is clear routing guidance against 29 sibling tools.

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