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

Annotations already declare readOnlyHint=true and openWorldHint=true, so no contradiction. The description adds context about returning 'a structured, audited deliverable' and that inputs are validated server-side, which goes beyond the annotations. It does not, however, disclose async behavior (despite the 'async' parameter) or other operational details.

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 long French paragraph with multiple example queries and a reference case. While the examples are useful, they are somewhat repetitive and the text could be more concise. The opening sentence clearly states the tool's purpose, but the middle section is a list of questions rather than structured guidance.

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?

With no output schema, the description should explain what the tool returns. It says 'structured, audited deliverable' but never specifies the format, fields, or how results are presented. It also does not mention async behavior or error handling, leaving significant ambiguities for a tool with 6 parameters and no output schema.

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 17% (only 'async' has a description). The description mentions filing types (10-K, 10-Q) and lookback implicitly via 'latest annual filing' and 'most recent SEC filings', but it does not clarify the distinction between cik and ticker, the focus enum values, or the meaning of lookback_months. It partially compensates for the low schema coverage but leaves significant gaps.

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 a 'Décodeur de filing SEC' with CFO-level expertise, listing concrete outputs like red flags, KPI movements, and executive summaries. It distinguishes itself from many siblings by focusing on SEC filings and structured deliverables, though it does not explicitly name alternatives.

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 provides several example queries ('Read the 10-K of <ticker>...', 'What has materially changed...') that imply usage scenarios, but it never explicitly states when to use this tool vs. alternatives like earnings_reviewer or ma_deal_screener. No exclusions or competing tools are mentioned.

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