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

Discloses the critical write semantics that annotations cannot convey: `built` and `notes` are appended while milestone_status is set per-milestone, which is consistent with destructiveHint=false and idempotentHint=true. It also surfaces a cost property ('No charge') and an escalation path, both selection-relevant details absent from the annotation block.

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 clauses, front-loaded with the scope constraint ('Updates ONLY the STATE layer'), followed by field semantics and then the escalation caveat. No filler sentences and nothing repeated from the schema.

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 2-parameter mutation tool with annotations and no output schema, it covers what changes, what cannot change, and the fallback behavior. The one omission is what the call returns or whether any confirmation/effect follows the write, which matters slightly since no output schema exists to answer it.

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 coverage is 50% – `patch` is only labeled '{ milestone_status?, built?, notes? }' in the schema, and the description adds real meaning by giving the milestone_status enum values and the append-vs-set behavior. `specId` is left unexplained beyond its pattern, which is a minor gap for a required 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?

Names a specific verb and resource ('updates ONLY the STATE layer of a saved spec') and enumerates the exact patchable fields (milestone_status, built, notes). The exclusion ('the intent and the plan cannot be changed here') carves out a clear boundary that separates it from plan/draft-oriented siblings.

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 clear when-to-use frame: state-layer progress updates only, plus an escalation rule ('if the intent looks wrong, ask the human') that prevents misuse. It stops short of naming the sibling tool to use for intent/plan changes, so the alternative is implied rather than explicit.

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