learn_tools

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is lighter. It adds genuinely useful behavior: batching up to 20 names and returning both schemas and availability. It does not contradict any annotation.

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?

A single tight sentence with the action front-loaded and no filler. The one weakness is that 'STEP 2' is a dangling reference unless the agent already knows the workflow.

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 one-parameter, read-only lookup tool with no output schema, the description covers purpose, batch limit, and return content (schemas plus availability). Minor gaps remain around name format and handling of unknown names.

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 0%, so the description must carry the parameter. It clarifies that 'names' are official operation names, accepted as a batch of up to 20, which meaningfully compensates for the empty schema. It stops short of specifying name format or behavior for invalid/unknown names.

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 ('Learn') and specific resources ('exact argument schemas and availability') scoped to 'official operation names', which distinguishes it from the sibling execute_tool. The 'STEP 2' framing hints at sequencing relative to a catalog step, but 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?

The 'STEP 2' prefix implies this follows a catalog/discovery step and precedes execution, giving implied ordering guidance. However, it never names the prerequisite tool or states when not to use this (e.g., for unknown/unlisted names), leaving the agent to infer the workflow.

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