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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the behavioral scope: it audits visible signal markers and order traces for skipped/duplicate/unfilled signals. It does not disclose details like whether it returns examples, how it handles missing data, or whether it requires a prior define_experiment_protocol call, though the protocolId parameter description hints at that.

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 a single sentence that front-loads the core action and scope. It is concise and readable. It could add a bit more context about the required parameters, but it earns its place without fluff.

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 tool with 12 parameters, 6 required, no output schema, and 42% schema description coverage, the description is somewhat thin. It tells the agent what the audit checks for but not what the output looks like, how to interpret results, or what the key parameters mean. The annotations cover safety, but the operational context is incomplete. The protocolId reference to define_experiment_protocol is helpful, but the rest of the required parameters (symbol, timeframe, startDate, endDate, source) are left unexplained.

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 only 42%, so the description should compensate for undocumented parameters. The description mentions protocolId implicitly ('for a required experiment protocolId') and the schema documents protocolId, inputs, caseStudyId, researchRunId, and mcpIdempotencyKey. However, parameters like symbol, timeframe, startDate, endDate, source, maxExamples, and duplicateWindowBars have no descriptions in the schema, and the tool description does not explain them either. The description adds the purpose of the audit but not the semantics of the date range, source, or duplicateWindowBars parameters.

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 states a specific verb ('Audit') and resource ('visible signal markers and order traces') and names the specific failure modes it checks for ('skipped, duplicate, or unfilled signals'). It also mentions the required protocolId. However, it doesn't explicitly distinguish itself from the many sibling 'analyze_*' tools, though the audit focus is fairly distinctive.

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 implies when to use it: when you need to audit signal markers and order traces for a protocol. It does not explicitly state when not to use it or name alternatives among the many analyze_* siblings. The context signals show 12 parameters and 6 required, but the description gives no guidance on how to choose this over analyze_trade_features or analyze_losing_trades, for example.

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