list_by_mitre_tactic

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

With no annotations provided, the description carries the behavioral burden, and its main signal is that 'List' denotes a read-only operation with no mutation or destructive side effects. It also discloses the scope ('all detections mapped to a tactic'), but adds nothing about pagination behavior, result ordering, or response shape — though the absence of an output schema makes some of that expected. The read-only profile and core behavior are conveyed, but little behavioral nuance beyond that.

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?

A single front-loaded sentence that leads with the action, names the resource, and includes useful inline examples. There is no filler, no repetition of schema details, and every word earns its place.

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 simple 3-param list tool, the description plus a fully documented schema covers the essential calling contract: what it returns conceptually and which parameters are needed. However, the crowded sibling field makes the missing routing guidance a genuine completeness gap, and the absence of any return-format or pagination context leaves the agent to guess at results beyond 'detections.' Adequate, but with clear gaps in an annotation-free, output-schema-free context.

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%, so the schema already documents tactic, limit, and source, earning the baseline 3. The description adds only marginal value: one new example tactic (credential_access) beyond the schema's examples, and the framing that results are 'all detections' for the given tactic. It does not clarify the source filter semantics or how limit interacts with the required tactic parameter.

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 specific verb and object — 'List all detections' — and pins the filtering dimension to 'MITRE ATT&CK tactic' with concrete example values (execution, persistence, defense_evasion, credential_access). The explicit 'tactic' wording separates it from the similarly named sibling list_by_mitre, and the filter dimension clearly distinguishes it from list_by_severity, list_by_process_name, and list_by_cve. There is no ambiguity about what this tool does.

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 provides no guidance on when to use this tool versus alternatives — it never mentions list_by_mitre, search_detections, list_by_severity, or any other sibling, and gives no exclusion criteria. The use case is only implied by the name and one-liner, which is inadequate given a sibling list of 120+ tools with several list_by_* variants. An agent gets no help deciding between this and the closely named list_by_mitre.

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