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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses specific behavioral traits: it performs one HTTPS read, has no destructive side effects, and never executes trades, wallets, settlements, or writes. It also details what is preserved (ranks, stress values, quality flags, nulls, dates, caveats). This significantly exceeds the annotation signal and provides actionable context.

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 longer than the minimal example but every sentence earns its place, covering purpose, parameters, behavior, and alternative in a structured way. It is front-loaded with the main use case and avoids fluff. Slightly verbose but not wasteful for a tool with multiple relevant facets.

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?

Given the tool has an output schema and rich annotations, the description covers all necessary decision points: when to use it, what it does, parameter constraints, and behavioral guarantees. It also mentions the sibling tool for structured JSON, completing the selection context. No significant gaps.

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% and each parameter already has meaningful descriptions (e.g., limit recommends 5-10 for concise summaries, style explains tone/density, offset paginates). The description merely restates this information (limit 1-100, offset paginates, style options) without adding new semantic value. Thus a baseline score of 3 is appropriate.

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 states the tool renders the Top Stressed screen into human-readable Markdown, with a specific verb ('explained', 'renders') and resource ('Top Stressed screen'). It explicitly distinguishes from the sibling deltasignal_top_stressed by noting the raw tool provides cheap structured JSON while this one gives premium human-facing summaries.

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 gives explicit guidance on when to use this tool ('when the user wants the Top Stressed screen explained in human-readable Markdown') and names the alternative ('Use raw deltasignal_top_stressed for cheap structured JSON'). It also clarifies that style only changes tone and density, not facts, helping the agent choose the right style.

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