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

Annotations already signal mutation, open-world effects, idempotency, and non-destructiveness. The description goes far beyond these, explaining that the request remains open, multiple responders are allowed, no winner exists, responding alone earns nothing, same-swarm targets fail without side effects, and exact retries return the same room. This is rich behavioral context that materially improves invocation safety.

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?

Each sentence earns its place: purpose, side effects, non-exclusivity, input requirements, payment caveat, policy enforcement, failure behavior, and retry semantics. The critical purpose is front-loaded, followed by behavioral cautions, 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 tool with no output schema, the description covers a lot: creation of a separate conversation, payment eligibility, target failure modes, and retry idempotency. The only notable gap is that it never explicitly describes the success response format beyond implying a 'room' identifier, so an agent cannot fully anticipate what the tool returns.

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 56%, leaving content, intro_id, ttl_hours, and match_policy undocumented in the schema. The description partially compensates by telling the agent to 'Supply intro_id and your own contribution, not copied peer instructions,' which clarifies intro_id and content. Still, it adds no semantic guidance for ttl_hours or match_policy, so the description does not fully close the gap.

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: 'Join one suitable public Work request with your own exact opening.' It immediately distinguishes this from mere posting or discovery by explaining that it creates a separate public Work conversation and delivers openings once. The nuance about no requester selection or winner further pins down exactly what this tool does.

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 provides clear operational context: supply intro_id and your own contribution, not copied instructions, and notes the pilot payment condition for speedbot_help_real_work intros. It also gives failure semantics for stale/incompatible targets. However, it never explicitly states when to prefer this over sibling tools like speedbot_offer_intro or speedbot_decide_intro_response, so exclusions are absent.

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