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

Beyond the annotations (which already declare read-only/idempotent/non-destructive), the description discloses real behavioral rules: it 'composes reads that already exist... and creates no store', 'OUR OWN ACTIVITY NEVER RAISES A SCORE', unreadable counts render as a dash rather than zero, and pay is proposed unless a job is funded. These are non-obvious semantics an agent could not get from the schema or annotations, and nothing contradicts the readOnlyHint.

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 core is front-loaded well (what it returns, then how it's composed, then caveats), but the prose is dense jargon and repeats itself: 'Free, keyless, read-only' appears mid-text and again as 'Cost and signer: free and keyless, nothing to sign.' The ALL-CAPS scoring rule and the experiment disclaimer add value but the duplication costs space.

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?

With an output schema present the description needn't detail return shape, and it still covers composition sources, scoring transparency, the worker proximity behavior, and the no-advice caveat. What's missing is placement relative to sibling tools like find_work or next_action, which matters given how crowded this tool family is.

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 coverage is 100%, so the baseline is 3; the description nonetheless adds meaning the schema lacks — that lat/lng makes 'nearness scores' count and that in the worker view 'remote work stays' even when out-of-radius work is dropped, plus the default radius of 25. It does not explain limit or the backer view's ranking inputs, but the added proximity semantics justify going above baseline.

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 concrete output — 'one ranked list of open claimable jobs, place conditions that are not yet covered, and open outcome bids' — and frames the two modes (backer/worker) with their questions. It is clear what the tool returns, but it never distinguishes itself from near-neighbours in the sibling list such as find_work, next_action, my_next_step, or place_standing, leaving the agent to guess which is the right entry point.

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 through the two views and the note that lat/lng switches on the worker proximity filter ('In the worker view, give lat and lng to see only work within radiusKm of you'). There is no explicit when-not guidance and no named alternative among the many overlapping siblings, so the agent must infer routing from the description's framing alone.

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