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

Annotations only declare readOnlyHint false and destructiveHint false; the description adds meaningful behavior beyond that: it reveals the practical limit (20 MB per file), the encoding requirement (base64), and the dashboard effect. This satisfies transparency 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 focused sentences: purpose+effect, constraints+input format, and source+example. Front-loaded with the core action and immediately actionable, with zero filler.

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 there is no output schema and annotations are minimal, the description covers the crucial aspects: what to attach, limits, encoding, and how to obtain IDs. It omits the mime parameter detail but that is optional and documented in the schema. Overall, sufficient for an agent to invoke the tool correctly in most scenarios.

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 only 40% (mime and data_base64 described), so the description must compensate. It adds context for interview_id and application_id via 'Get interview ids from get_application' and the example, but still leaves filename semantics implicit. The size and base64 constraints are helpful but not parameter-specific enough to fully compensate for the gap.

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?

Purpose is clearly stated: 'Attach prep material to a specific interview' with a specific outcome ('so the user sees it next to that round in the dashboard'). The verb+resource combination is precise and distinguishes it from the sibling attach_file by specifying interview-specific attachment.

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?

Provides explicit prerequisite: 'Get interview ids from get_application' and a concrete example showing required parameters. It also sets usage boundaries (max 3 files, size limit). Missing explicit comparison to alternatives like attach_file, but the interview-specific wording implies the correct choice.

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