List tools a worker can use

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description adds genuinely new behavior: each entry carries a risk class and communicate/write_crm/external tools "do things people will want to review." It also discloses the pagination profile ("Returns every tool in one page") and the concrete return shape, which prevents an agent from hunting for a cursor or guessing at fields.

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 with the definition, then the downstream purpose, then the risk warning, then the return contract — a natural reading order with no filler. Every clause carries information an agent needs: what it lists, why to call it, what the risk field means, and that results are unpaginated.

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 read-only, well-annotated list tool with a full output schema, the description covers purpose, prerequisite timing, safety implications of the returned risk classes, and pagination. The only omission is guidance on using the filter parameters to narrow a large inventory, which the schema handles but the description leaves implicit.

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 100% and all four parameters are documented in-schema, so the baseline of 3 applies. The description echoes the `source` enum values (builtin vs action) and clarifies that actions belong to the workspace's connected integrations, but it says nothing about `search`, `provider`, or the `response_format` default that an agent would otherwise have to read from the 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?

States a specific verb and resource ("Lists the tools a worker may be given") and immediately ties the output to its downstream use: the names to pass as `tool_names` on heliyos_workers_create / heliyos_workers_update. It also enumerates what the list contains (builtin tools plus integration actions) and attaches a risk class, so an agent can distinguish this from heliyos_workers_list/get without opening a schema.

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?

"Call it before creating a worker" gives an explicit prerequisite and names the two sibling tools that consume the result, which is the main routing decision an agent faces here. It stops short of stating when not to call it (e.g. skipping the lookup when tool names are already known) or when to narrow with search/source/provider rather than pulling everything.

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