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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds genuinely new behavioral context by warning that the response is a single page plus vendor pagination metadata rather than the full portfolio. That is exactly the trap an agent would fall into. It stops short of describing filter matching behavior or the response envelope.

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 short sentences with no filler, and the highest-value warning about pagination is placed second where it is still prominent. The telegraphic style costs a little readability but wastes no space.

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 13 optional parameters, no output schema, and only 54% schema coverage, the description leaves real gaps: no return-shape detail, no explanation of filter combination or defaults, and no routing to arthur_get_unit. It does cover the pagination contract, which is the single most important behavioral fact for this tool.

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 only 54%, so the description must carry weight for the undocumented params (_q, city, postcode, unit_ref, unit_status, unit_vacant, unit_owner_id). The field list ('vacancy, availability, unit type, market rent and location') reads as returned data rather than as filter semantics, so it does not clarify whether these are exact-match filters, and it says nothing about what _q searches.

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 the resource ('Units') and enumerates the data it exposes (vacancy, availability, unit type, market rent, location) plus the endpoint 'GET /v2/units'. However, it is written as a noun-phrase fragment with no verb, and it never explicitly distinguishes itself from the singular sibling arthur_get_unit or the other list tools beyond the resource 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?

There is no statement of when to use this listing versus arthur_get_unit for a single unit, nor which filters to apply for which scenario. The only guidance is about paging ('this is one page, not the whole portfolio'), which is useful but covers only one decision.

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