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

The description discloses the memory loop (recall up to 12, write up to 3), the serving model, cost per call, and that the response names the serving model. These go well beyond the sparse annotations (readOnlyHint false, openWorldHint true, destructiveHint false) and give the agent a concrete model of side effects and output.

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 moderately long but every sentence carries useful information: tier, contract, model, cost, when-to-use, input, and output. The trailing '(20 MESH/call, a tool · cognition)' is metadata that could be trimmed, and the opening repeats the title, but overall it is front-loaded and well-structured.

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 tool with one nested object parameter and no output schema, the description covers the input shape (albeit simplified), the return fields, model, cost, and usage guidance. Aliases are documented in the schema, so the description plus schema together are complete enough 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?

The description's 'Input: {think: string}' omits the required outer 'input' wrapper described in the schema, which could mislead invocation. It adds no information beyond the schema's 100% parameter descriptions and fails to mention the optional 'character' parameter, so it subtracts rather than adds value.

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 clearly identifies this as the Smart tier of agent-brain, sharing the identical memory loop but served by claude-sonnet-5 for deeper reasoning. It distinguishes from the sibling agent-brain by model, cost, and quality tradeoff. The purpose is specific and immediately understandable.

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 explicitly names agent-brain as the fast default and instructs to pick this tier when answer quality matters more than price. This gives a direct when-to-use vs alternative. The statement 'identical contract' also implies the same use cases as the base tier.

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