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

Annotations indicate readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds valuable behavioral context: the tool stores a baseline per query×model and compares previous runs, plus pricing details ($0.10/call). This goes beyond the bare annotation flags, though it doesn't detail rate limits 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?

Two sentences: the first captures the full core function, the second covers billing granularity. No filler or redundancy; information is front-loaded.

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?

The description covers the tool's stateful behavior (stored baseline), output (changed answer + cited domains), and cost model. Since there is no output schema, it appropriately describes return values. Minor gaps: no explicit statement about first-run baseline creation or auth/payment integration, but the overall picture is complete for a moderately complex tool.

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 100% — every parameter (lang, models, queries, maxConcurrency, openrouterApiKey) has a detailed description. The top-level description repeats the 'row per query x model' billing concept already in the schema but adds no new parameter-level semantics. Baseline 3 applies.

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?

Description clearly states the tool's function: asks an LLM about user queries, compares answers against a stored baseline, and reports changes in the answer text and cited domains. This specific monitoring/alerting use case distinguishes it from sibling tools like crawler access checker or overview tracker.

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?

Description implies when to use: when you want to track how LLM answers to your chosen queries change over time. It provides context through 'stored baseline' and billing, but does not explicitly name alternatives or exclusion criteria. The schema's model and query descriptions add usage guidance about row multiplication and limits.

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