postmortem

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

Annotations already carry the safety profile (readOnlyHint=true, idempotent, non-destructive), so credit goes to what the description adds beyond them: the explicit failure mode 'rejects action items without owner and due date' and the required document sections. It stops short of saying whether the document is persisted or returned, which is the one behavioral question left open.

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?

Two sentences, zero filler, and the core artifact description is front-loaded ahead of the validation constraint. Every clause conveys information the agent cannot get from 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?

The output schema means return values need no explanation, and annotations cover safety, but this is an 11-required-parameter, fully nested-array tool with a 0%-described schema. Missing guidance on timestamp ordering (started ≤ detected ≤ mitigated ≤ resolved), severity semantics, and array size expectations leaves the definition thin for the tool's complexity.

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% across 11 required parameters, so the description has to carry the load. It does map to several fields (impact, timeline, contributing factors, action items) and flags the owner/due-date requirement, but never mentions title, severity levels, the four incident timestamps, whatWentWell, or the action-item 'kind' enum, leaving over half the surface undocumented in prose.

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 artifact ('generate a blameless postmortem document') and enumerates exactly what it is built from: timeline, impact, detection, contributing factors and owned action items. That framing cleanly separates it from adjacent siblings such as runbook or decision_record, which produce different artifacts from different inputs.

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?

Usage is only implied: the input set (startedAt, detectedAt, mitigatedAt, resolvedAt) signals 'call this after an incident is resolved.' No explicit when-to-use, when-not-to-use, or named alternative is given, so the agent must infer prerequisites such as whether the incident must be fully closed before a postmortem can be generated.

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