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

Beyond the annotations, the description adds rich operational context: the keyless funding model ('YOU pay from your own wallet'), explicit non-actions (never spends/holds/signs), the retirement-lane queueing behavior, the semantic distinction 'provision, not offset,' and a dated operator pause ('paused by operator order since 2026-08-04'). This is exactly the kind of context annotations alone cannot convey.

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, each carrying distinct weight: purpose and deliverable, behavioral boundaries, and operational status of the retirement lane. The most decision-critical information is front-loaded in the first sentence, and the dated pause note is a compact, high-value operational detail. No filler.

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 100% parameter coverage, an output schema, and annotations covering safety and idempotency, the description only needs to cover purpose, input modes, and operational caveats — and it does all three. Minor residual ambiguity: all parameters are optional, so behavior with no inputs is unclear, and the exact impact of the paused lane on the returned packet is not spelled out. These are small gaps given the richness of surrounding structured data.

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 3 baseline applies. The description adds structural meaning the flat schema lacks by grouping parameters into two call modes: 'place + problem' (latitude, longitude, query) versus 'board packet id' (workId). The schema hints at this through 'with query' and 'Or free text,' but the description makes the input-mode structure explicit.

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?

States a specific verb ('provision') and exact inputs ('place + problem (or a board packet id)') and enumerates the concrete deliverable: 'a bounded packet with scope, standards-registered method, proof requirement, tCO2e estimate, and the keyless funding path.' This clearly differentiates it from siblings like find_work (searching), get_work_packet (retrieving), and prepare_funding (executing payments).

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 opening clause makes the trigger condition explicit — use this when you have a place + problem or a board packet id and want to produce provisioned work. The exclusions ('never spends, never holds funds, never signs') tell the agent what this tool will not do, implying that execution belongs elsewhere, though it stops short of naming a specific alternative sibling for that case.

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