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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds substantive behavior beyond them: the data is an end-of-month 'as at' snapshot, the default is latest, and the returned content changes shape based on occupation and points.

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?

Front-loaded with the resource and scope, then the branching rules. Three sentences with no filler, though the middle sentence packs several conditions and runs long.

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 and does so well, describing what is returned in each branch (whole stream + top occupations, single occupation with trend, above/at-point counts) so the agent knows the result shape before calling.

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 would be 3, but the description adds real interpretation: points means 'how many EOIs sit above and at that score', occupation switches the output to that occupation's pool plus trend, and month is an end-of-month snapshot. This goes beyond 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+resource (EOI pool snapshot) with the exact source (Home Affairs SkillSelect) and a precise scope: backlog for subclasses 189/190/491 by points and state. An agent can separate this from get_189_invitations or get_state_nomination 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?

Clearly explains the calling contexts: omit occupation for the whole stream plus top occupations, include occupation for that occupation's pool and 12-month trend, pass points to position a score in the pool. It describes output variation by argument rather than explicit when-not/alternatives, so no exclusions are named.

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