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

readOnlyHint=true already covers the safety profile, and the description adds genuinely useful behavior beyond it: a hard 25-records-per-page cap, the fact that line items are omitted from results, and which fields free-text search actually scans. It does not mention any auth/permission constraints or how the API responds on unknown predicates, but for a read-only list endpoint the disclosed behavior is above adequate.

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 definition, then search scope, filtermode values, the line-item exclusion and the pagination cap – every sentence carries operational information. The trailing 'Current RMS: GET /opportunities' is provenance rather than usage guidance, a minor piece of low-value text, but the overall structure is tight.

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?

For an 8-parameter, nested-object list tool with no output schema, the description covers what is returned in outline (dates, state, charge totals), what is deliberately missing (line items), pagination limits and alternative tools. The complex filters/sort/include parameters rely wholly on the schema, which documents them well, so only the return-shape detail is thin.

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 baseline is 3. The description earns an extra point by expanding the filtermode enumeration well beyond the schema's 'live, all, quotations, orders, not_invoiced' (adding inactive, enquiries, drafts, invoiced, not_invoiced, needing_prep) and by restating search coverage, both of which help an agent pick valid values without guessing.

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?

Opens with a specific verb+resource and immediately disambiguates the domain term: opportunities are 'the enquiries, drafts, quotations and orders for a rental job'. It also delineates scope against siblings by stating line items are excluded and naming current_rms_get_opportunity / current_rms_list_opportunity_items as the alternatives, so an agent can separate it from other list tools without reading their schemas.

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 frames the tool as the paginated browse/search entry point and explicitly routes line-item needs to two named siblings, plus enumeration of filtermode values signals the filtering scenarios it supports. It stops short of a full when-when-not statement (e.g. when to prefer get_opportunity by id over listing), but the practical context is unambiguous.

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