fow_capabilities

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

Annotations already cover readOnly/idempotent/non-destructive; the description adds genuinely new behavioral context: it 'does not execute recipes' and returns 'exact required/optional fields, accepted selector values, examples and guidance'. This clarifies the tool is pure introspection rather than an action, which the annotations alone would not convey. It stops short of describing pagination or size bounds for the 'full' view.

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?

Front-loaded routing sentence, then prerequisites, effects, and a concrete example call. Every element is useful, though the final 'Exact help' sentence is somewhat clunky and partly overlaps the earlier routing statement.

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?

An output schema exists, so return contents need not be described. For a meta-discovery tool the description covers routes, required companion parameters, prerequisites, and side-effect scope, leaving nothing an agent needs before invoking it.

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 baseline would be 3, but the description adds conditional dependency semantics the schema does not express: recipe requires recipe_name, operation requires operation_tool plus operation_name. That routing-to-parameter mapping is real added meaning.

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: 'Discover what Flower can do and how to call it', with concrete sub-capabilities (bounded tool summary, workflow recipes, exact operation inputs, diagnostic catalog). This is clearly distinguishable from all the action siblings like fow_run, fow_traceability, or fow_goal, which perform work rather than describe it.

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?

Gives explicit routing conditions for each view ('recipe needs recipe_name, operation needs operation_tool and operation_name') and a prerequisite statement ('No project, database mutation or optional provider is needed'). It does not explicitly say when to prefer a concrete sibling over this discovery tool, but the route-to-use mapping is clear.

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