opencdr_case_extensions

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context that authorization follows the deployment mode (Fleet authority in fleet mode, standalone Core in Core mode) and that no lookup is executed, but it never says what data shape returns (a fixed 20-item page?) or what happens at the page boundary.

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?

The Fleet/Core authority statement is repeated twice in near-identical wording ("Uses Fleet authority directly in fleet mode" and "In fleet mode this tool uses the Fleet authority directly; Core mode uses standalone Core"), wasting a third of the text. The lead sentence is front-loaded, but the duplication leaves less room for substantive detail.

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?

With three undocumented parameters, no output schema, and zero schema description coverage, the description should explain the kind discriminator, pagination via 'after', and the meaning of the fixed twenty-item read. None of that is present, so an agent could invoke it with a valid-but-meaningless 'kind' value.

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%, so the description must carry parameter meaning, and it does not: the required 'kind' discriminator is never explained (no allowed values for indicators vs provider-results), and 'after' is never identified as a pagination cursor. Only the case ownership link is loosely implied.

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 states a verb and resource ("Read ... case-owned indicators or historical provider-results"), which is more specific than the name alone, but the unqualified "20" is unexplained and the notion of "extensions" versus case data returned by opencdr_case_read is never clarified. An agent cannot confidently tell this apart from the sibling case tools.

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 when-to-use guidance, no mention of when to prefer opencdr_case_read or opencdr_case_active, and no prerequisite for the required case_id/kind pair. The statement "never executes a lookup" is behavioral, not a usage rule, so the agent is left to infer selection criteria.

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