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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior. The description adds useful context about the data source and returned fields, including English/French titles, structural breakdown, and validity, without contradicting annotations.

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?

Three tightly written sentences that front-load the purpose, then give symbol format guidance, then scope exclusion. Every sentence contributes useful selection or invocation information.

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 simple read-only lookup tool, the description covers the source, return contents, symbol syntax, and scope boundary. Parameters are fully documented in the schema, and although there is no output schema, the description lists the relevant returned fields.

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 both symbol and version are already documented in the schema. The description reinforces the symbol format (subclass versus full group/subgroup) but adds little beyond the schema and does not discuss version semantics.

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 ('Look up one IPC symbol') plus the source (WIPO IPCPUB) and return contents. It clearly excludes CPC, but does not explicitly name the IPC siblings such as ipc_search, ipc_children, or ipc_versions, so sibling differentiation is only implicit through 'one'.

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 clear single-symbol lookup context and an explicit when-not boundary for CPC. It does not tell the agent when to prefer ipc_search, ipc_children, or ipc_versions, so alternatives among the IPC tools are not fully covered.

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