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

Annotations already supply safety hints (write, non-idempotent, non-destructive, closed-world), and the description adds far beyond them: strict 5-minute TTL with roster-drop behavior, failure codes (MESH-OFF, MESH-BAD-INPUT), mutation gate (confirm=true vs dry_run=true), counting rules (human bearers count, software_nodes and downloads do not), and the return field presence_ttl_ms=300000. This is unusually rich operational disclosure. No contradiction with the annotations found.

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?

The first three sentences are excellently front-loaded with purpose, routing, and exclusions. But the remainder is one dense stream of telegraphic clauses ("Downloads are not live. Read-only suite-presence is ON by default." ...), and the ambiguous "Read-only suite-presence is ON by default" line could momentarily misread as the tool being read-only. Every clause carries information, but the lack of structure makes it harder to parse than necessary.

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 complex mutation tool with 6 parameters, a mutation gate, three error codes, and classification rules, the description covers call conditions, exclusions, failure modes, return values, and TTL semantics almost exhaustively. The output schema covers the return shape, so the description need not repeat it. Only minor gaps remain (duplicate node_id behavior, reversibility via mesh_leave), which is negligible against this coverage.

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 the baseline is 3; the schema already documents required-ness, enums, and node_id pattern. The description adds meaningful gate semantics (confirm/dry_run interplay) and presence-to-count meaning. However, it mentions kind, plane, and bearer as if they were settable parameters, yet none exist in the schema and additionalProperties:false would reject them — a genuine description/schema mismatch that could mislead an agent.

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?

"Register one product node into the QNM rollup" gives a specific verb, resource, and scope, and the qualifier "first presence, not a TTL refresh" sharply differentiates it from mesh_heartbeat. The description also names the siblings it is not (mesh_nodes, mesh_enable, runtime_session_open), so an agent can disambiguate without opening any other 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?

Explicit when-to-use: "Use this when transmission radios are LIVE and a catalog product should appear in live/locked/isolated counts." Exclusions are equally explicit: "Do not use it for refreshing an existing node, reading the roster, enabling radios, or opening an account session" with four named alternatives. Nothing is left to inference.

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