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

Annotations already establish readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it discloses the model source, the verdict categories returned, and the 24-month EOI life that bounds the estimate. It doesn't state latency or data recency, but the model attribution and verdict taxonomy are strong additions beyond the 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?

A single dense sentence that front-loads the verb, model, required inputs, and return payload. Every clause earns its place, though the long list of returned fields makes it slightly heavy to scan.

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?

Given a read-only, idempotent, open-world predictor with no output schema and 100% schema parameter coverage, the description is complete enough: it names the model, the inputs, and the full set of return verdicts and metrics an agent needs to interpret the response. Nothing essential is missing for correct invocation.

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 100%, so the schema already documents all five parameters, setting a baseline of 3. The description goes further by explaining what eoiMonth is for (queue position by lodgement month) and implying firstLodgedMonth's role in the 24-month expiry, adding interpretive value over the raw schema text.

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 (estimates) and resource (subclass 189 EOI invitation timing via a named queue model), and distinguishes itself from sibling get_189_invitations by describing it as a predictive estimate rather than a record fetch. An agent can route between the predictor and the raw invitation list without opening either 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?

Clear context: you give occupation and points, and optionally eoiMonth for a queue position by lodgement month. It names required inputs but doesn't explicitly say when NOT to use it versus get_189_invitations or get_eoi_backlog, so the agent must infer the predictor-vs-data distinction from the wording.

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