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

Annotations already carry destructiveHint=true and readOnlyHint=false, lowering the bar. The description adds useful behavioral context beyond annotations: mutations are self-logged, writes need UUIDs, and declare_pm_exception signals a human-decision requirement. It does not disclose confirmation flows, return behavior, or which specific modes are destructive, but the annotation covers the destructive profile adequately.

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 description is compact and scannable, using CURATE/EXECUTE/DOCUMENT/GOVERN to compress a large surface area into a few sentences. It front-loads the tool's identity and every sentence carries some operational guidance. Minor jargon like 'facade' and the all-caps category labels are slightly cryptic, but the density is appropriate for the tool's breadth.

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?

Given 78 parameters, 28 modes, no output schema, and destructive behavior, the description is a minimum-viable orientation rather than a complete invocation guide. It supplies the critical guards (external-only log_decision, UUIDs) and broad mode families, but relies heavily on the schema for mode-specific semantics and does not mention return shapes or confirmation requirements.

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 91%, so the schema already documents most parameters and baseline is 3. The description itself adds little parameter-level meaning beyond the UUID requirement and a hint about declare_pm_exception. Mode-specific parameter relationships are left to the schema's per-parameter descriptions, which is acceptable given the high coverage.

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 identifies a 'PM decision facade' and enumerates concrete action families with verbs and resources: curate evidence/deal-breakers, execute create/update/dispatch/delete Solutions, record Outcomes, and govern living docs/coverage/schedules/knowledge/strategy. It does not name one single operation, but for a 28-mode tool the mode enum supplies the granularity. The write-focused framing also helps separate it from read/analysis sibling 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?

It explicitly delimits log_decision to external decisions ('mutations log themselves') and states a hard prerequisite for writes ('require UUIDs'). It also clarifies one mode's special meaning (declare_pm_exception on claims). It does not provide routing guidance for all 28 modes or name sibling alternatives explicitly, so it stops short of a 5.

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