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

With annotations already covering readOnly/idempotent/non-destructive/closed-world, the description still adds substantive behavior: what a returned report contains (status, counts, sections, manifest), the resolution rule that a partial never replaces the last complete report, that results are withheld when any source chat is outside the AI read scope, and that there is no AI-credit charge. The untrusted-data warning is a useful safety cue. It stops short of describing pagination, size limits, or what an empty/absent report looks like.

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 core action, and every clause carries real information (scope, coverage semantics, access restriction, cost, safety). It is dense and slightly run-on in the coverage explanation, but there is no filler.

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 single-parameter read tool with an output schema, the definition covers resolution behavior, access restrictions, cost, and safety framing, so an agent can decide reliably whether a report will come back. The one real hole is the undocumented definition_id, which is the only required input.

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 coverage is 0%: definition_id has no description and only a numeric-string pattern, so the description is the only place meaning could be added — yet definition_id is never mentioned. An agent must infer that it identifies which report definition to read, and nothing explains valid sources for that id.

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?

States a specific verb and resource ("Read a stored period report") and immediately defines the exact scope: the last complete report plus, when newer, the latest attempt. That framing also implicitly separates it from list_period_reports (enumeration) and get_period_report_run (a single run) without ambiguity.

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?

The description conveys usage context (read the current stored report, prefer the complete one over a partial) but never names an alternative tool or says when to call get_period_report_run or get_period_report_evidence instead, nor how to obtain a valid definition_id. Usage is implied rather than guided.

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