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

The annotations only say non-read-only, non-destructive, closed-world; the description goes well beyond them by disclosing that no signatures or bot changes are needed, that Pitbi reads public fills, that the proof order never fills, that checks are rate-limited to once a minute, that proofs expire, and that the address is never exposed. That is exactly the extra context the annotations cannot carry. Not fully transparent on idempotency (relinking an already-linked account) or what a failed check implies.

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 purpose is front-loaded, but the body degrades into telegraphic fragments ('new_proof=true if it expired.', 'The address is never shown.') and crams the entire proof procedure into one overlong sentence. The rate limit and proof-expiry rules — arguably the most operationally important facts — are buried mid-paragraph rather than structured as steps.

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 five-parameter mutating tool with an output schema, this covers the essentials: what linking means, the full proof workflow, status checking, expiry handling, rate limits, and privacy of the address. Return-value details are legitimately delegated to the output schema, and the remaining gaps (api_key, subaccount) are minor relative to the workflow it describes.

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 0%, so the description must carry all five parameters. It explains check, new_proof, and the allowed delay_seconds values (0, 3600, 86400 for all holdings), but says nothing about api_key (the sole required parameter) or subaccount, and leaves delay_seconds' default of -1 and the meaning of 'for all holdings' unclarified. Partial compensation only.

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 first sentence states a specific verb and resource: declare a Decibel trading account once for all strategies, and it explains that per-strategy attribution is handled by update_strategy rules rather than here. That separates it from update_strategy and create_strategy. It never mentions the near-sibling prove_account or strategy_positions, so an agent still has to infer whether this or prove_account is the right proof path.

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?

Strong procedural guidance: call with no arguments for status, place and cancel the proof order first, then call with check=true at most once a minute, and use new_proof=true if the proof expired. These are explicit when-to-call-with-what conditions. What is missing is routing against alternatives — no statement of when to prefer this over prove_account, or what to do if the account is already linked.

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