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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's extra behavior is appropriately supplementary. It adds a meaningful behavioral caveat: vetoed signals never count in the win rate, and the outcome field appears only once scored. This goes beyond the structured annotations without contradicting them.

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?

Two sentences carry all essential information: what is returned, the time window, ordering, fields, scoring condition, and the win-rate exclusion. There is no fluff or redundant restatement of the tool name.

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 simple read-only list endpoint with no output schema, the description is complete: it specifies time range, sort order, included data, and the conditional presence of the outcome. Annotations cover safety semantics, and the schema covers parameters, leaving nothing critical missing.

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 both parameters (limit and symbol) are already documented in the input schema. The description adds no parameter-specific guidance, but it does not need to carry that burden. Baseline 3 is appropriate because the schema handles parameter semantics fully.

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 names a specific verb and resource: it lists signals cancelled by the BTC regime veto, constrained to the last 7 days, newest first. It also clarifies that these carry the veto reason and, when available, the outcome they would have had. This clearly differentiates it from siblings like get_open_signals and get_signal_ledger.

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 context is implied: an agent should call this when it needs vetoed signals from the last 7 days, and not when it wants signals that count toward the win rate. However, there is no explicit when-to-use vs alternatives, no mention of when to prefer get_signal_ledger or get_open_signals, and no stated exclusion criteria.

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