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

Beyond the read-only and idempotent annotations, the description discloses meaningful behavior: ranking prioritizes same kind/category and shared agent capabilities, higher quality, and agent-ready tools. It also explains that Dangerous look-alikes are listed first and labelled 'Dangerous: avoid', that the queried tool is excluded, and that unknown slugs produce soft suggestions with did_you_mean and isError false.

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 front-loaded with the core use case and then efficiently packs in ranking behavior, dangerous labeling, fallback behavior, and a next-step recommendation. It is dense but each clause generally earns its place, though some phrases such as 'same kind/category and shared agent capabilities first' are information-heavy.

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 list tool with no output schema, the description covers the important behavioral context: what is returned, how alternatives are ranked, how dangerous tools are surfaced, and what happens on an unknown slug. It does not explain the limit behavior or the returned fields in detail, but these are minor gaps for a tool whose schema and annotations already cover the basics.

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 67%, with the slug and kind parameters already documented in the schema. The description mentions unknown slug resolution behavior but does not add meaning for the limit parameter or explain how result counts are controlled, so it stays at the baseline for partially covered 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 states a specific verb and resource: it returns other tools ranked as alternatives to tool X and explicitly excludes the queried tool. The purpose is clear, but sibling differentiation is limited to mentioning get_tool as a follow-up rather than contrasting with search_tools or find_tools_for_task.

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 gives clear usage context via the question 'What can I use instead of tool X?' and tells the agent to use get_tool on a selected alternative for the full report. It also describes fallback behavior for unknown slugs, but does not explicitly state when not to use this tool versus sibling discovery tools.

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