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

Annotations already cover readOnly, idempotent, openWorld and non-destructive, so the bar is lower, and the description still adds substantial behavioral context: the four possible verdicts (next round, later round, not within the 24-month EOI life, stalled), the returned artifacts (estimated month, fast/slow scenarios, EOIs ahead, wait at other points scores), and that sources/conditions/pagination are preserved. The only blemish is that it declares "returns English natural-language text" while the locale parameter defaults to zh-CN/Simplified Chinese, a minor internal tension rather than an annotation contradiction.

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?

Two sentences, front-loaded with the core purpose before inputs and return behavior, and every clause carries information (model provenance, inputs, verdict set, return format). It is dense but not padded; slightly long sentences keep it from a 5.

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 no output schema, the description carries the burden of explaining returns and does so concretely (verdict categories, estimated month, fast/slow scenarios, EOIs ahead, cross-score waits, natural-language format). Combined with required inputs and the model's provenance, an agent has everything needed to call and interpret this tool correctly.

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 in detail (locale enum, points range, YYYY-MM patterns, occupation code resolution rules). The description only restates the occupation and points inputs and gestures at the EOI date of effect, adding essentially no meaning beyond what the schema provides. Baseline 3 is appropriate.

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 and resource ("Estimate when a subclass 189 EOI could be invited") and names the exact model behind it (One U Education's queue model, same as oneuedu.com's predictor). This is distinguishable from the sibling get_189_invitations (actual invitation data) and get_eoi without opening either schema, since the description makes clear this is a forward projection, not a record lookup.

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 tells the agent what inputs to supply (internal occupationCode, points, optionally EOI date of effect) and points back to search_occupations for resolving the code, which is real usage guidance. However it never states when to prefer this over get_189_invitations or get_eoi, nor any exclusions or prerequisites (e.g., only relevant to subclass 189 EOIs onshore/offshore). Usage is implied rather than explicit.

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