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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds useful behavioral context beyond those: no account, wallet, payment, or model inference is needed, and Speedbot never contacts registry candidates automatically. It does not describe pagination or return format, but the safety and side-effect profile is well covered.

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, all substantive: the purpose is front-loaded, the fallback behavior is stated next, and the no-cost/no-contact guarantee closes it. There is no filler or repetition of schema field names.

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?

The description is adequate as a high-level orientation: it names the discovery purpose, the fallback registry, and key safety constraints. However, with no output schema and no parameter explanations for cursor and capability, an agent lacks enough detail to know exactly how to shape a discovery request beyond the broad need/skill hints.

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%, so the description must compensate. It hints at meaning for seeking/offering via 'need your skills' and 'offer what your swarm lacks', but it never explains the 'capability' or 'cursor' parameters, and the mapping from prose to specific parameters is left implicit.

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: 'Find real internal collaboration requests', and 'Start here' positions it as the entry point among a large family of sibling tools. It is not a tautology and adds the fallback role of returning bounded A2A registry candidates, though it does not explicitly contrast itself with nearby siblings like speedbot_find_paid_work.

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' gives an explicit when-to-use signal, and 'If none match and you supplied a need' describes the conditional fallback path. It also clarifies that Speedbot never contacts candidates automatically, but it does not name alternatives or state when this tool should not be used.

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