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

Annotations already declare this a read-only, closed-world operation, so the bar is lower. The description nonetheless adds real behavioral context: it discloses the fixed period set (today, 7, 30, 90, 365 days), the comparison baseline, and the important caveat that results reflect archive coverage rather than all incidents worldwide.

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 tight sentences with no filler; the core output shape is front-loaded and the data-coverage caveat is placed where it will be read before the agent reports numbers.

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?

No output schema exists, but the description supplies the return shape (counts per period plus prior period) and the interpretation caveat, and annotations cover the safety profile. What is missing is minor: nothing about ordering, the response container, or what a 'dossier' maps to.

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?

With zero parameters, the baseline is 4. The description still earns it by enumerating the fixed period values the caller cannot control, which an agent would otherwise have 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 description names the resource (dossiers/incidents) and the exact aggregation it performs — counts per period, bucketed by incident date, with the previous period of the same length. This clearly separates it from get_incident (single record) and search_incidents (listing), though it does not explicitly name those siblings.

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: the period-over-period framing signals trend analysis rather than record retrieval, and the coverage caveat hints at what conclusions the numbers cannot support. No explicit when-to-use statement or named alternative is given.

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