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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false), it discloses the key behavior that the amendment is inert until accepted by the user in the Pryzm dashboard or explicit conversation agreement, and that closed steps and validated phases are immutable. That is real mutation-safety context an agent would otherwise misjudge. Minor gaps: atomicity of multiple operations and what happens to a rejected amendment.

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?

Front-loaded with the core action in the first clause, then a compact bulleted operation list, then constraints and acceptance semantics. Every sentence carries information; the only slight redundancy is restating 'not closed' three times, which is defensible for scannability.

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 mutation tool with no output schema and nested operation objects, the description covers the critical semantics: operation shapes, immutability constraints, and deferred-commit behavior. What remains uncovered is the PlanStepIn field set and the return value, but annotations already declare the non-destructive, non-idempotent profile, so the remaining gap is modest.

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%, so the description must carry the load. It does well for the operations array: each op value is mapped to the fields it needs (phase, position, step, step_id). However, plan_id and justification are only implied ('active plan', 'with a justification'), and the step object's required fields (title, instruction, checklist, deliverable) are never described, leaving a meaningful nested-payload gap.

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 ('Proposes a change to an active plan, with a justification') and then enumerates the four operation kinds (add/remove/modify/move), which pins down exactly what the tool does versus plan_create or plan_validate. An agent can tell this is an amendment proposal, not an execution, without opening the schema.

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?

Gives per-operation applicability rules ('a step that is not closed' for remove/modify/move; phase+position+step for add) and an explicit alternative path: 'to correct a closed step, add a correction step.' It also states the acceptance condition. It stops short of naming a sibling tool or stating when not to propose an amendment at all, so it is strong context rather than full routing guidance.

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