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

Beyond the annotations (readOnlyHint, destructiveHint), the description adds meaningful behavioral details: the output structure (each cell = tags + lead + source URL + survey date), optional marks derived from a declared rule file, and the fact that it shares a generator with /compare pages. It also clarifies that no ranking or scoring is produced. This adds context beyond the annotations.

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 main purpose. It packs useful details without redundancy, though the list of ledger items and the output format sentence are somewhat dense. Overall, it's efficient with no filler.

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 tool with one array parameter, the description covers the essential details: the comparison criteria, the cell structure, the marks behavior, and the 'single throat' generator consistency. No output schema is provided, but the description explains the return format well enough. Missing are error handling or edge cases (e.g., duplicates), but these are minor for such a tool.

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?

The only parameter 'slugs' is fully documented in the schema (description, minItems, maxItems), so schema coverage is high. The tool description adds a small nuance by saying '2-5 published systems/tools', which clarifies the requirement of being published, a slight enhancement over the schema but not substantial. Baseline of 3 is appropriate.

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 a specific action ('side-by-side comparison') and a specific resource ('published systems/tools on ledger items'), with concrete examples of ledger items. It does not explicitly name sibling tools but differentiates by noting 'No ranking, no score' and 'Same generator as the /compare pages', which helps disambiguate.

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?

Usage is implied: use when you need a side-by-side comparison of 2-5 systems on predefined criteria. However, there is no explicit 'when not to use' or mention of alternatives (e.g., if you need ranking, use another tool). The 'No ranking, no score' note hints at exclusions but does not direct the agent to a specific sibling.

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