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

With no annotations, the description carries the behavioral disclosure burden, and it does disclose important traits: Talon does not sign, output is not a fill size or an exit, and it defines 'clustered' behavior. This is valuable safety-relevant context. It omits return-format details and does not explicitly say read-only, but the non-signing disclaimer substantially covers the main risk.

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 extremely compact and front-loads the core metaphor and criteria before moving to categories and exclusions. There is no filler. The telegraphic, fragment-heavy style ('smart vs sniper', 'Not a fill size. Not an exit.') slightly hurts readability, but every phrase earns its place.

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 tool, the description covers the core concept well and includes important disclaimers. However, it never explicitly states what the output looks like (e.g., a list of wallets with labels), and it leaves '7-figure name', 'smart', 'sniper', and 'desk' undefined. The absence of an output schema makes these gaps more significant.

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 input schema is empty and there is nothing to clarify. The description instead explains the tool's conceptual output categories ('smart vs sniper', 'clustered'), which is the relevant semantic content. Baseline 4 applies for zero-parameter tools.

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 gives a recognizable metaphor ('Nansen for this chain') and specific cohort criteria ('Wallets that bought a 7-figure name under $200k'), which implies an analytics tool that identifies wallet groups. However, it lacks an explicit operation verb like 'returns', 'lists', or 'identifies', and key terms such as '7-figure name', 'smart', and 'sniper' are undefined. It does not clearly distinguish itself from the many talon_* sibling tools beyond cryptic exclusion phrases.

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 meaningful negative guidance: 'Not a fill size. Not an exit. Talon does not sign.' tells an agent this tool is not for execution, fills, or exits. 'Snipers do not fire the desk' gives a pipeline-specific exclusion. It stops short of naming alternative tools or stating a positive 'use this when...' condition, so it misses the top score.

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