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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, yet the description adds genuinely new behavioural facts: computation happens in server memory, nothing is saved, no credits are issued, no payments are sent, and money values are illustrative cents rather than real prices. It also describes the failure mode (an error that says what is invalid) and the receipt/disclosure artefacts returned alongside results. Nothing here contradicts the read-only, non-destructive annotations.

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?

It is front-loaded with the usage trigger and anti-scope before the return-value sentence, and every sentence carries information (scope, constraints, prohibitions, outputs). It is dense and runs as one continuous block with heavy dash/clause chaining, which costs a little scanability for a ~130-word description.

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?

There is no output schema, so the description usefully summarises the return payload (scenario, modelled reserve, sale, shares, per-member allocations, closing checks, status flags, error detail, source receipt) and the read-only contract. For a nested one-parameter tool at 0% schema coverage, the main remaining gaps are the undocumented `kind` enum and the required-block/version constants, which an agent would have to infer from the schema alone.

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 single parameter is a deeply nested object, so the description has to carry the semantics — and it does, explaining that member shares total 10000 basis points, that all projects must share the same program/method/vintage pool key, and what the policy fields govern (reserve, stewardship, treasury, sale size, price). It stops short of explaining the project `kind` enum values (ecohedge/landscape/grassland) or the `status`/`version` constants, which remain undocumented anywhere.

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 names a specific verb and resource: model a pooling scenario of members with 10000 bps shares, projects sharing one pool key, and a reserve/stewardship/treasury/sale/price policy. It explicitly distinguishes itself from certification, pricing, eligibility and recording tools, and points at the sibling example_pooling_draft for schema shape, so an agent can separate it from its siblings without opening a schema.

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?

It gives an explicit trigger ("Use when a person wants to model their own pooling scenario"), an explicit anti-trigger list ("Do not use it to certify credits, set prices, check eligibility or record anything"), and names the alternative ("Start from example_pooling_draft if you need the shape"). It also states the input precondition: consented or synthetic inputs only.

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