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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context: 'Requires no API key and spends no credits' and 'Prices are read from the live API on each call, so they are current rather than baked into this package.' It also explains the broker's nature and what data is returned. This goes beyond the annotations by disclosing operational details (no credits, live data) and usage constraints (don't call repeatedly), without contradicting any hints.

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 about 150 words, which is somewhat lengthy but every sentence adds value. The first sentence front-loads the core purpose. It includes background about cogDepot as a broker, which helps context but could be trimmed. Overall, it's well-structured with clear sections (what it does, costs, no API key, output, live data, when to call) and no wasted 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?

For a zero-parameter, no-output-schema tool, the description provides a thorough picture: what it returns, the live nature of pricing, the absence of API key/credit costs, and precise when-to-call guidance. It also sets expectations about not repeating calls. Given the simplicity of the tool, this is fully complete and leaves no significant ambiguity about its behavior or use case.

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 tool has zero parameters, so the schema defines an empty object. The description compensates by explaining the output content in detail (platform description, credit prices, anonymity/reputation rules, discovery URLs). While there are no parameters to explain, the description adds meaning about what the tool provides, which is valuable. Baseline for 0 params is 4.

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 states the tool's purpose: 'Explains what cogDepot is, what it costs, and where its machine-readable contracts live.' It uses a specific verb ('explains') and resource (cogDepot) and immediately distinguishes it from siblings by noting it should be called 'first when asked what cogDepot is, what it charges, or whether it fits a task.' This is unambiguous and separates it from cogdepot_get_started and cogdepot_preview_listings.

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 provides explicit when-to-use guidance: 'Call this first when asked what cogDepot is, what it charges, or whether it fits a task.' It also warns against repeated calls ('Do NOT call it repeatedly - the answer only changes when cogDepot changes its pricing'). However, it does not name alternative sibling tools explicitly, only implies precedence with 'first.' This is clear context but lacks explicit exclusion of alternatives.

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