Pattern mitigate

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

Annotations already establish read-only/idempotent behavior, but the description adds substantial context beyond them: it discloses the envelope fields (recommendation_basis, recommendation_audit.capability_sources, snapshot_age_seconds), the caveat that a stale snapshot may mis-flag mute as enabled, and the behavioral contract that the agent surfaces the menu and waits for a user pick. This is exactly the kind of disclosure that goes beyond structured annotations.

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?

Content is front-loaded with routing and the core purpose, and every section is relevant. It is dense with bolded emphasis and some repetition (the 'NOT this envelope' point is restated), which costs a little tightness, but the length is largely justified by the routing contract and chaining instructions.

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 router whose output schema exists, the description covers everything an agent needs: the trigger, the reachability-first semantics, the chaining path, the audit/staleness fields, and a pointer to the behavior contract doc. No gap that would cause a wrong invocation remains.

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 parameters are already documented; the description nonetheless adds meaning by clarifying that pattern accepts a symbolMessage identity or tenx_hash from a prior tool, that service scopes single-service options, and that snapshot_id drives which capability sources populate the audit. Marginal but real added value over the schema baseline.

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 (return the env-gated capability menu for a given pattern) and enumerates the four tiers it reports on (drop_at_analyzer, drop_at_forwarder, mute_at_10x, compact_at_10x). It also explicitly draws the boundary against siblings, declaring it is a 'REACHABILITY-FIRST router' and not the savings/action tool. An agent can distinguish it from log10x_cost_options and the action tools without opening any 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?

Names the exact triggering condition ('when a previous tool surfaced a high-cost pattern and the user asks what should I do / how do I drop this') and the prerequisite routing (call log10x_start first on the session's first cost question). It routes to the specific alternatives (log10x_cost_options for the action menu, then the action tool for the snippet) and warns not to auto-route until the user picks.

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