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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds useful intent context (updates happen in place to keep one authoritative record), but says nothing about whether fields are partially or fully replaced, permission requirements, or reversibility of an edit — meaningful gaps for a mutation tool.

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?

Three compact sentences: purpose first, rationale second, doc link last. No padding, and the key point is front-loaded. The doc URL is dead weight for an agent but does not disrupt readability.

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 5-parameter mutation tool with no annotations beyond the safety hints, no output schema, and zero schema descriptions, the definition is thin. It omits update semantics (partial vs full replacement), which fields are actually revisable, and what a successful revision returns.

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 carries the full burden, yet it only enumerates the four values of the `kind` enum. The required `decision_id` and the `summary`, `detail`, and `task_id` parameters are left entirely unexplained, so the agent learns almost nothing about what to pass.

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 precise verb and resource ('Revise a recorded decision, learning, preference or constraint on a project'), including the set of record kinds it operates on. It is clearly distinguishable from purely additive siblings like log_project_decision, though it never names that sibling explicitly.

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 a trigger condition ('when the thinking changes') but no explicit when-not, prerequisites, or named alternative. The clause about avoiding 'contradictory duplicates' implies log_project_decision is the wrong tool for revisions, but the agent must infer that routing decision itself.

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