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

Annotations only declare read-only/idempotent safety, and the description adds the substantive traits: 10 results per page, default relevance ordering that includes paid featured placement, and a featured_placement marker the agent should disclose when presenting results. That disclosure obligation is behavioral guidance an agent could not derive from any structured field.

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, front-loaded with the trigger, then output shape, then the exclusion. No filler, and the paid-placement caveat is placed where it will be read before results are presented.

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?

Six optional parameters, an output schema, and full annotation coverage; the description supplies the trigger, what comes back, pagination cadence, ranking caveat and a scope exclusion. Nothing an agent needs in order to call or present this correctly is missing.

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 enum values, defaults and ranges are already documented, and the description's parameter-relevant content (MARN, city/suburb matching, relevance ordering) largely duplicates it. Baseline 3 applies; the featured-placement explanation is the one piece of added meaning.

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 ('find or compare registered migration agencies in Australia') and enumerates the searchable dimensions (city, suburb, state, agency name, agent name, MARN). An agent can tell immediately what this tool does; the only soft spot is mild overlap with find_registered_agent, which it does not name.

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?

Gives an explicit trigger ('use this when someone wants to find or compare...') and an explicit exclusion ('Do not use for visa advice or eligibility'). It stops short of routing to the sibling tools (find_registered_agent, get_migration_agency, list_agency_locations) for agent-level or detail lookups, so the boundary with siblings is inferred rather than stated.

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