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

Annotations already declare readOnly/idempotent/destructive=false, so the description is free to add genuinely new behavioral facts: all output series are returned (not one), each is reduced, the forming bar is excluded by default, and handles behave differently under dataMode. Missing any note on cost/latency of computing a full catalogue run, which would matter for openWorldHint=true.

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?

Four sentences, each carrying a distinct fact — scope, return shape, input mode, and the forming-bar default — with the most decision-relevant information (what you get back) front-loaded. No filler.

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 an 11-parameter tool with no output schema, the description adequately conveys the output contract and the two input paths. It leaves the dataMode trade-off and enum semantics entirely to the schema, which is acceptable given 73% coverage but not fully self-contained.

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?

With 73% schema coverage the schema does much of the work, but the description adds real meaning: symbol vs ref as alternative data sources, plot as 'usually omit' because other series give the reading meaning, and includeForming's default. reduce and exchange/timeframe are left to the schema enums.

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 ('Run any indicator in the catalogue') and immediately clarifies the return contract: every output series (Donchian's three bands, MACD's line/signal/histogram) plus conventional levels. This distinguishes it from chart_add_indicator and chart_toggle_indicator, which mutate the chart rather than compute series.

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?

'Pass a symbol to load and compute in one call, or a handle to reuse data' gives a clear selection rule between the two data paths, and the forming-bar sentence sets an explicit default. It stops short of naming a sibling to use instead (e.g. catalog_search to obtain studyId) or saying when to prefer chart_add_indicator, so no true exclusion guidance.

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