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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds the useful behavioral fact that it returns aggregate counts restricted to 'published' entities and a last-changed timestamp — meaningful context an agent would not get from annotations alone.

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?

A single well-formed sentence with zero filler; the count outputs and the freshness timestamp are front-loaded and nothing is repeated from the schema or annotations.

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 a zero-parameter, annotated read tool this is essentially complete: the agent knows what is counted, that only published items count, and that a last-updated value is returned. With no output schema, a slightly clearer statement of the return shape would have been the only improvement.

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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly implies a no-argument, global summary with no filtering scope to specify.

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 a specific verb ('Get the number of') and three concrete resources (marine contractors, places, categories) plus a freshness metric ('when the data last changed'). The emphasis on counts implicitly separates it from list_categories and list_places, which return entries rather than totals, though no sibling is named explicitly.

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?

Usage is only implied: an agent can infer this is the summary/count tool rather than the enumeration tools, but the description never states when to prefer it over get_listing or the list_* siblings. No exclusions or prerequisites are given.

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