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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: it discloses that unsupported clauses are reported rather than guessed, that the return set is expr/universe/notes/unsupported-clauses, and that no data is fetched — telling the agent this is a pure parse/compile step.

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?

Three tight sentences: purpose plus syntax example, then return contents, then the no-fetch caveat. Front-loaded with the core action and zero filler; every clause carries information the agent needs.

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 does the work of naming the return fields (expr, universe, notes, unsupported clauses) and the fidelity guarantee. Minor gaps remain: it does not say what happens on wholly invalid scan text (error vs. empty notes) or how the returned spec is consumed downstream.

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%, so both parameters are already documented and the baseline would be 3. The worked example goes beyond the schema's bare "StockCharts scan text" by showing the actual authoring syntax (bracket clauses, rank by, ROC) an agent must supply, which materially reduces format guessing.

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 and resource ("Translates a StockCharts.com scan") and names the two deliverables (FinzData signal formula, ready-to-run backtest spec). The concrete scan example makes the domain unambiguous, and "No data is fetched" draws a usable boundary against execution-oriented siblings like backtest_stockcharts_scan or run_backtest, though no sibling is named explicitly.

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 is strongly implied: this is the translation step that produces a spec you would then backtest, and "never guessed" signals it is safe on partially supported input. But there is no explicit statement of when to pick this over backtest_stockcharts_scan (which presumably translates and runs) or run_backtest, and no stated prerequisites or exclusions.

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