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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds meaningful behavioral detail beyond those: it returns EVERY output series, reduces each series, includes conventional indicator levels for interpretation, and excludes the forming bar unless explicitly requested. This gives the agent a clear mental model of the tool's computation and default behavior.

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 three tight sentences with no waste. It front-loads the core purpose, then packs return behavior, examples, invocation modes, and a default exclusion into the remaining sentences. Every clause earns its place.

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 a 10-parameter tool with no output schema, the description covers the essential return shape, invocation modes, and a key default behavior. It could more precisely define what 'reduced' means for each reduce mode or note exchange/market defaults, but an agent can select and call the tool correctly with the information provided.

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 70%, so the description is expected to add some meaning. It does: 'symbol' vs 'ref' is clarified as load-and-compute versus reuse-handle, 'reduce' is implied by 'each reduced,' and includeForming is explained via 'forming bar is excluded unless you ask for it.' It does not clarify exchange defaults or the exact reduce modes, but it adds real value beyond the bare schema.

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 opens with 'Run any indicator in the catalogue,' a specific verb and resource, and immediately clarifies the tool's output behavior with concrete examples (Donchian, MACD). It distinguishes itself from chart-focused siblings like chart_add_indicator by emphasizing that it computes and returns reduced output series rather than manipulating a chart.

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 clear usage context: run any catalogue indicator, and provides two invocation routes ('Pass a symbol to load and compute in one call, or a handle to reuse data'). However, it does not explicitly state when not to use this tool or compare it to alternatives such as chart_add_indicator or catalog_search, leaving the selection criteria mostly implied.

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