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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: results are leads not proof, absence of a technique does not imply safety, no key/address/time is retained with the signal, and non-code input is rejected. It does not describe the shape of the returned list, which keeps it from a 5.

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 output is front-loaded in the first sentence, and each subsequent sentence carries distinct information (one-signal constraint, interpretation caveat, privacy handling, input refusal). The phrasing is slightly awkward ('for a person to read', the colon-heavy privacy sentence), which keeps it below a 5.

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, fully documented lookup with no output schema, the description covers what comes back, how to interpret it, and how errors arise. Annotations handle the safety profile, so nothing essential is missing, though a hint about result shape or volume would make it 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?

Schema description coverage is 100%, and the schema already says the parameter is 'a fixed code, never free text' with two examples. The description reinforces the single-signal-per-call constraint and adds refusal behavior for invalid input, but contributes little semantic detail about the code format itself beyond what the schema provides.

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 first sentence states the resource (a posture signal) and the returned content (the ATT&CK techniques it may point to), which lets an agent tell it apart from general graph traversal siblings like graph_node or graph_neighbors. The verb is implicit ('read' from the title) rather than explicit, and no sibling is named for contrast, so it falls short of a 5.

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?

'Ask about ONE signal per call' constrains invocation, and 'anything that is not a plain signal code is refused' sets an input boundary, which is more than nothing. However, there is no guidance on when to reach for this tool versus graph_lookup, graph_node or graph_search, so routing is left to inference.

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