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

Annotations declare destructiveHint=true and idempotentHint=true but can't express why; the description supplies exactly that by spelling out replace-previous-decision semantics, that omitted reasons/note preserve saved values, and that an empty list or string clears them. It also states the return ('the saved review'), which the tool has no output schema for.

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 sentences, front-loaded with the action and decision values, then merge semantics, then ID provenance and return. No restatement of the name or title and no wasted clauses.

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?

Covers what an agent needs to call it correctly: mutation effects, partial-update behavior, ID source, and return value. It omits permission/ownership failure modes and the size limits on reasons/note, though the latter are in the schema.

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?

With 0% schema description coverage the description must carry the load, and it does for four of five params: candidateId provenance (from sourcing_read), selection values, and the omission-vs-empty semantics of reasons and note. sessionId is only implied by 'owned sourcing session' — nothing explains what a session id is or where to get one.

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 ('Save the user's review decision') and enumerates the decision domain (liked, shortlisted, skipped) scoped to one candidate in an owned sourcing session. That scope plus the pointer to sourcing_read makes it distinguishable from the sibling read/outreach tools 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?

Gives the context that selects this tool (recording a decision on a candidate in a session you own) and routes ID acquisition to sourcing_read. It does not name an explicit alternative or a when-not condition, so it stops short of full routing guidance.

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