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

Beyond annotations, the description discloses non-obvious behaviors: input sanitization (URLs, wallets, payment header names stripped), rejection of extra keys, rate-limiting on discovery pulses, free-versus-paid behavior ('Never charges, never runs research'), and the shared 10-call trial across paid tools. This substantially exceeds what annotations (readOnly, idempotent, non-destructive) convey.

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 description is dense and front-loaded with the core purpose ('Pick exactly one MentionForge tool for a goal'), followed by essential constraints. While every sentence carries operational weight, several clauses are packed into run-on sentences that may reduce parseability, and the sibling-routing nuance ('sending a sibling tool name still keyword-routes') could be phrased more directly. Still, 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 the tool's complexity (a router with one parameter), the description covers all operational aspects: what it does, what inputs are acceptable, what happens with malformed inputs, billing/rate-limit behavior, trial sharing, and explicit routing alternatives. An output schema exists for return values, so no description of return format is needed. The definition is complete for correct invocation.

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% for the single 'need' parameter, but the description adds critical semantics beyond the schema's definition: 'Pass need as a goal sentence, not a tool name' and the consequences of sending a tool name (keyword-routes from remaining words). It also clarifies that extra keys are rejected, which shapes how the parameter should be used. Baseline 3 is elevated because of this meaningful addition.

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 states a specific verb and resource: 'Pick exactly one MentionForge tool for a goal.' It explicitly distinguishes itself as a free router from sibling tools and names alternatives (get_health, get_pricing, research_mentions) for specific needs, so an agent can tell it apart without opening schemas.

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?

The description gives explicit when-to-use guidance ('when you are unsure which tool to call'), when-not-to-use conditions with named alternatives ('for liveness use get_health instead; for price use get_pricing instead; for live mentions use research_mentions'), and clear constraints on input format (goal sentence, not tool name). This leaves no ambiguity for routing decisions.

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