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

Annotations already carry the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description does add real value by disclosing data scope — metadata/approved fields only, excluding secrets, contacts and original files — which is information the annotations cannot convey. It says nothing, however, about result granularity, pagination behavior, or whether trend data is pre-aggregated.

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 read-scope constraint is stated up front. Brevity here is efficient rather than padded, though the space saved is used for nothing that would help invocation.

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?

Adjusted: no output schema exists, three parameters are undocumented, and the tool sits among a dozen overlapping compliance-analytics siblings — the description does not do enough for an agent to call it confidently or choose it. The data-scope sentence helps but leaves the core gaps of filter semantics and sibling differentiation unaddressed.

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 0%: limit, query and offset have only types and bounds, no semantics. The description compensates for none of this — most importantly, what the free-text `query` filter searches over (employee, location, date, credential type?) is entirely unspecified, forcing the agent to guess.

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 verb+resource pair 'Read authorised compliance trend' is a genuine statement of purpose, but 'trend' is never defined (over what period, along what dimension). It also fails to distinguish itself from close siblings like get_compliance_distribution, get_location_compliance_analytics, get_site_compliance_analytics, or get_dashboard_analytics.

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 indication of when to call this versus get_compliance_distribution, get_copliancy_summary, or the various analytics siblings. No prerequisites, no exclusions, no context about which question this answers that the others do not.

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