Is this message worth sending?

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

Annotations already establish readOnlyHint, idempotentHint, destructiveHint=false, so safety is covered; the description adds non-obvious division-of-labor context — 'the server checks references and rules; the calling agent judges meaning and truth' — and confirms 'It never dispatches a message.' That clarifies the tool's boundaries well beyond the annotations, though it doesn't describe scoring determinism or failure modes.

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?

Roughly five sentences, front-loaded with the core action, then inputs, outputs, behaviors. Every sentence carries information — sibling routing, required inputs, return shape, the hold rule, the server/agent split. Slightly dense but no filler.

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?

Given a nested 10-parameter schema, an output schema, and full safety annotations, the description covers what's left: prerequisite ordering, the evidence discipline, and the decision semantics. Since an output schema exists it needn't detail return values, and it correctly doesn't over-explain them. Minor gap is how the nested assessment object maps to the per-dimension ratings, but the schema carries that.

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 80%, so the schema already documents most parameters, and the enum-free fields are largely self-describing. The description enumerates the categories of input to supply (message, context, evidence, per-dimension judgments), which corroborates but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 description names a specific verb and resource — enforce the message value rubric on an evidence-backed assessment — and states exactly what the tool returns (send/revise/hold, score, reasons, required changes). It also distinguishes itself from the sole sibling by instructing the agent to read get_message_rubric first, so an agent can route between the two without opening either 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 gives explicit sequencing ('Read get_message_rubric first') and a concrete fallback rule ('Missing context returns hold'), which tells the agent when a call is premature. It stops short of a full when-not-to-use statement, but the sibling routing and the hold-on-missing-context rule cover the practical decision points.

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