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

With no annotations, the description carries the full burden and does so richly: it discloses the grading thresholds that shape the output (e.g., mid scores reported as normal), the per-timeframe breakdown, payment amount, retry behavior on 402 challenges, and that the data is snapshot-based and informational only.

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 dense but every sentence carries substantive information — purpose, output format, grading logic, payment, retry, and sibling comparison — with no filler. It could be more visually structured (single paragraph, many clauses), but the content is front-loaded and efficient enough for an agent to parse.

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 one-parameter tool with no output schema and no annotations, the description is exceptionally complete: it covers input semantics, output components (score, inflState, reading, period, timeframe breakdown), grading rules, payment mechanics, and when to use `pitch` instead. An agent needs nothing else to invoke it correctly.

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 coverage is 100% (the schema already explains the `symbol` parameter with examples), so the baseline is 3. The description adds meaning beyond the schema by detailing the covered universe (47 series, 10 countries, US liquidity/rates/jobs), giving more concrete examples (US-PCE, US-PPI, US-FED, US-RRP, US-M2, JP-CPI, DE-CPI), and explaining how the symbol maps to the output verdict.

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?

States a specific verb+resource ('Return the inflation-thermometer verdict for one official macro series'), names the covered universe, and distinguishes itself from the sibling `pitch` tool by scope and output detail. An agent can tell exactly what this tool does.

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?

Explicitly contrasts with `pitch` ('The free `pitch` tool shows a live verdict for this market's showcase symbol only — this tool answers ANY symbol in the covered universe'), giving a clear condition for selecting this tool. It also clarifies snapshot-based, informational-only behavior and payment expectations.

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