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

Annotations already establish readOnly, idempotent, non-destructive and open-world, and the description usefully goes beyond them: 'Keep source and full snapshots local' discloses a privacy/local-data constraint, 'Caller-reported outcomes are not verified execution' warns that inputs are untrusted, and the exclusion list makes clear it is stateless and non-persisting.

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?

Four short sentences with the capability statement front-loaded and constraints following; no filler. The dense, protocol-flavored vocabulary costs some clarity but nothing is redundant.

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 12-parameter tool with nested objects, a non-trivial enum, and no output schema, an agent needs guidance on what projection data to supply and what 'caller-reported outcomes' implies. The description covers boundaries and one caveat but gives zero parameter-level orientation, leaving a substantial gap.

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% across 12 parameters (including nested checks/impact/pending objects with enums), so the description carries full burden and largely fails. Only indirect hints exist ('stage-specific' for stage, 'project projection' for the input bundle); goal, needs, stack, checks, impact, pending, hasContext and the revision fields are never explained.

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 clear verb (Get) and resource (stage-specific capability selection and concrete next actions) with the scope 'from a caller-approved project projection'. It does not name or contrast any sibling such as resolve_task_capabilities or get_daystruct_validated_guidance, and terms like 'capability selection' and 'project projection' are invented jargon an agent must infer.

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?

No explicit 'use this when' condition or named alternative is given. The closing exclusions ('does not acquire, execute, store project context or send reminders') do implicitly delimit it from session/event siblings, which is real routing value, but the agent must still infer when to pick this over resolve_task_capabilities.

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