get_failed_messages

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds only that package filtering is unsupported, but does not explain return shape, pagination, time-range behavior, or how failures are scoped; it also contradicts the schema's package parameter.

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?

The description is a single compact sentence with no filler. However, its two clauses are not well structured around the tool's actual invocation needs, since the unsupported-package claim is not connected to the schema.

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 tool with five optional parameters and no output schema, the description is insufficient: it does not explain time filtering, result limiting, integration flow scoping, or what metadata is returned. Annotations cover safety, but the description leaves important invocation details missing.

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% for five parameters, so the description must carry parameter meaning. It mentions only 'package' and says its filtering is unsupported, while the schema still exposes a package parameter, leaving limit, startTime, endTime, and integrationFlow completely undocumented and the package behavior confusing.

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 clear verb and resource, 'Retrieve failed message metadata,' so the operation is identifiable. It does not distinguish this from adjacent siblings such as get_recent_failures or analyze_failure, so it is clear but not sibling-differentiating.

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 only usage-like statement is that package filtering is unsupported, which is a limitation rather than guidance on when to choose this over search_messages, get_recent_failures, or get_message_details. No explicit when-to-use or alternatives are provided.

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