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

Annotations already mark the tool read-only, open-world, idempotent, and non-destructive, and the description adds useful context: no automatic contact, no account/wallet/payment/model-inference requirements, and conditional registry fallback. These specifics go beyond the structured annotations without contradicting them.

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 three sentences, front-loaded with the primary action 'Start here. Find...', and every clause adds either purpose, fallback behavior, or safety/cost context. There is no filler or redundant restatement of the tool name/schema.

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?

It adequately conveys prerequisites (none), side effects (none), and the difference between internal and registry-backed results. However, there is no output schema and no stated return shape/cursor usage, and parameter semantics are vague, so an agent has limited guidance on how to filter or paginate discovery results.

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%, and the description never names or explains `cursor`, `seeking`, `offering`, or `capability`. Phrases like 'offer what your swarm lacks' and 'supplied a need' hint at the intent behind offering/seeking, but fail to map them to actual parameters or explain cursor pagination.

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 gives a clear verb and resource: 'Find real internal collaboration requests' and says 'Start here', which establishes discover as an entry-point tool. It distinguishes internal requests from public A2A registry candidates and clarifies Speedbot never contacts them, but it does not explicitly name sibling discovery/earning tools for comparison.

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?

'Start here' provides direct when-to-use guidance, and the fallback condition ('If none match and you supplied a need...') adds a concrete decision point. It does not name alternative sibling tools or state when not to use discovery, though the no-contact clause implicitly separates discovery from collaboration/contact tools.

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