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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the description's job is to add context — which it does: it discloses the authentication/ownership scoping ('belonging to the authenticated user and organization') and the crucial semantic that a missing entry is not evidence of no evaluation. It stops short of describing ordering, pagination behavior, or typical result volume.

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?

Three short sentences, zero filler: what is read, how to interpret a negative result, and what the tool is not. The scope statement is front-loaded and the caveat follows logically.

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?

There is no output schema, so the description carries the burden of explaining results, and it does so partially — it frames the return as an audit/decision log and include_details is documented in the schema as adding market_snapshot, sdk_response and order_intents. What is missing is the default result shape and ordering for a listing tool, though this is a minor gap for a simple read.

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 limit, offset, strategy_id and include_details are already documented, and the description does not elaborate on them. It does add one meaningful constraint on strategy_id — that the strategy must belong to the authenticated user and organization — but otherwise leaves parameter meaning to the schema, matching the baseline of 3.

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 uses a specific verb and resource ('Read the MangroveAI agent evaluation decision log') and immediately scopes it to a single strategy owned by the authenticated user. It also carves out a negative boundary ('does not read platform evaluation records'), which separates it from the evaluate_* siblings that produce evaluations rather than listing them.

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?

Usage is only implied: an agent can infer this is the tool for checking past evaluation decisions on a strategy, and the note that an absent audit record means 'unknown activity' is genuinely useful interpretation guidance. However, no alternative tool is named (e.g., get_strategy or list_backtests) and there is no explicit when-not-to-use condition.

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