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

With no annotations, the description carries the full behavioral burden. It discloses non-execution ('Talon recommends, it does not fill'), non-signing, GET/POST semantics, polling cadence, and the 'not financial advice' caveat. It could add auth/rate-limit details or explain domain jargon like 'sign' and 'avoid,' but the core behavioral traits are transparent.

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?

Every sentence earns its place. The core purpose is front-loaded, followed by actionable usage and explicit limitations. The fragment style is compact and scannable while preserving meaning.

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 single-optional-parameter tool with no output schema, the description covers invocation, polling, return source, and limitations well. The main gap is that 'live target book' is not expanded with the fields an agent should expect, but the reference to calls/say and the trade recommendation role provide enough operational context.

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%, so the baseline is 3 even without parameter detail in the tool description. The description adds context that holdings are submitted via POST to get a diff and that sizing/exits remain the caller's responsibility. It does not elaborate on individual optional fields, which is acceptable given the schema already covers them.

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 the tool as an autonomous trader for Hands that returns the live target book, and distinguishes its read endpoint (GET) from the holdings submission (POST). It is specific about resource and action, though 'autonomous trader' is immediately qualified by 'it does not fill,' which softens the label. It doesn't fully distinguish itself from the many talon_* siblings, but names calls/say as complementary resources.

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?

Explicit usage guidance is provided: poll every 5–15 minutes, POST holdings to get a diff, GET for the book only, and read calls/say for conviction. It also states exclusions—Talon does not fill, sign, or override caller sizing/exits, and says to honor avoid. This gives clear when-to-use and when-not-to-expect guidance.

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