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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds domain behaviour the annotations cannot: IOCs sharing an entity_ref are related (MD5/SHA-1/SHA-256 of one file) and each IOC exposes an IDS flag and false-positive risk — both genuinely useful for interpreting results. It says nothing about pagination behaviour or default ordering, though the cursor and limit parameters are documented in the schema.

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 short paragraphs with the core action and scope front-loaded and the filters enumerated immediately after. The closing sentence on IDS flags and false-positive risk borders on restating output fields that the published output schema already covers, which is the only mildly redundant content.

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 7-parameter, read-only list tool with full schema coverage and an output schema, the description supplies the non-obvious pieces an agent needs: report scoping, the entity_ref grouping concept needed to read results correctly, and the filter dimensions. It omits any mention of pagination despite the cursor parameter and does not point at competing IOC tools, leaving small gaps for a tool with ten siblings.

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 100% schema description coverage, the schema already documents every parameter including examples for types, tags and categories and the cursor semantics. The description restates the same filter set (type, tag, category, text) without adding format, matching or precedence rules, e.g. whether multiple filters AND together. Baseline 3 applies.

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 ('List the IOCs') together with the scope ('of one Rösti report') and the filterable dimensions, so an agent can tell this is report-scoped IOC retrieval rather than a global search. It never names the adjacent tools (search_iocs, lookup_ioc, lookup_iocs), so the differentiation is inferable from the scope phrase rather than stated.

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: 'of one Rösti report' signals this is the tool for pulling everything attached to a known report_id, and the optional filters suggest narrowing within that set. There is no explicit guidance on when to prefer search_iocs or lookup_iocs instead, and no statement of prerequisites such as needing a report_id obtained from get_report or search_reports.

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