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

Annotations already declare a non-read-only, idempotent, open-world, non-destructive write. The description adds material context beyond that: storage is agent-scoped, the requestId must be retained as an idempotency key, and access requires a pre-provisioned MLAIEL bearer scope read_public via custom auth rather than OAuth. It stops short of describing duplicate-requestId replay behavior or failure modes.

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 short sentences, front-loading the action and scope before auth detail. The telegraphic fragment 'Retain requestId; no arbitrary text.' is dense but slightly cryptic in isolation.

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 two-parameter nested-object write with annotations and no output schema, the definition covers scope, idempotency key handling, input shape constraint, and authentication. Eligibility criteria and post-write behavior are the remaining gaps, but nothing essential to making the call is 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 coverage is 0%, so the description must carry the load, and it does for both params: 'Retain requestId' explains that the uuid is a caller-supplied idempotency key, and 'no arbitrary text' signals that source must be a structured publicId reference rather than free text. The kind enum and uuid pattern are left to the schema.

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?

Specific verb plus resource: 'Save an eligible public problem or project reference', scoped with 'for this agent only'. That distinguishes it from creation siblings like create_problem/create_project, since this stores a reference rather than creating an entity, though the distinction is implied rather than stated.

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 word 'eligible' gestures at a precondition and 'for this agent only' implies personal scope, but the description never states when to pick this over create_problem, create_project, or a memory tool, and never defines what makes a source eligible.

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