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

Annotations only declare write/destructive/open-world; the description adds real behavior the agent could not infer: anchored notes are surfaced to whoever touches that code and go stale on rewrite, decisions never go stale, and a decision holds each agent's first write there once. It also states the return value ("returns their ids"). No contradiction with destructiveHint=true, since superseding/retiring notes is implied.

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 purpose, then anchor behavior, then the decision special case; each sentence carries distinct information. The decision sentence is dense with parenthetical examples and a multi-clause consequence, which costs a little readability but not a wasted sentence.

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 7-parameter, zero-required mutation tool with no output schema, the description covers the main behavioral risks: staleness, decision permanence, write-holding, and supersession's retirement effect. It doesn't address interaction between fact and facts, validation failures, or whether setup/repo binding is required, leaving minor gaps.

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 100%, so baseline is 3, but the description goes beyond it: it supplies anchor syntax examples (path::symbol, file, dir/) and explains the special semantics of kind="decision" — its permanence and the write-hold it triggers. That meaning is not visible from the enum values alone.

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 opening sentence gives a specific verb and resource ("Save a durable team fact") and immediately scopes it by exclusion ("a decision, constraint or gotcha, not code state"). Between that and the explicit anchor/decision guidance, an agent can tell this is the write-side counterpart to a retrieval tool without opening a 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?

It states when to use the tool (durable facts, anchored facts about specific code, standing human decisions) and gives concrete trigger phrasing for decisions ("remove X", "never Y", "only Z"). What's missing is routing against siblings such as defer_intent or claim — nothing tells the agent when a fact belongs in a note versus an intent or a claim.

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