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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value beyond that: it promises exact figures from the database, never estimates, and uses 'same filters as list_records' to communicate filter behavior. There is no contradiction with the annotations.

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, zero filler: the first states capabilities and constraints, the second gives quotable example queries, and the third gives a domain-specific guardrail. Information is front-loaded and every sentence earns its place.

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?

Combined with annotations and an output schema, the description covers purpose, filter behavior, metrics, grouping, and one important audience note. It is not fully self-contained because it relies on 'same filters as list_records' for filter syntax, and `metric_field` semantics are implicit at best. For a tool with 6 required parameters and no schema parameter descriptions, this falls just short of complete.

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 input schema has 0% description coverage, so the description must carry the semantic load. It explains metric kinds (count/sum/avg/min/max), grouping by field or date bucket, record type, and filter parity with list_records. However, it never explicitly defines 'metric_field' or when it is required for sum/avg/min/max, which is a notable gap for a 6-parameter tool.

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 opens with a specific verb and resource: computes aggregate metrics over one record type, with grouping and filtering. It unambiguously distinguishes itself from list_records by saying it returns exact figures rather than individual records. The 'how many', 'per stage' examples make the tool immediately recognizable.

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?

It gives explicit trigger phrases ('how many', 'per stage', 'average fee', 'placements per month') and even advises 'aggregate applications, not candidates'. It does not explicitly say 'when you need actual records, use list_records', but the same-filters-as-list_records relationship and aggregate-versus-list contrast provide strong contextual guidance.

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