observer_context

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

Annotations already mark the tool read-only and idempotent; the description adds useful behavioral detail: the result is 'Local, read-only' and an empty string when nothing has been learned. This goes beyond the annotations and clarifies the tool's side-effect-free nature.

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 packed sentences with no filler. The core purpose, output format, and fallback behavior are all front-loaded and immediately actionable.

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 the simple read-only nature, optional parameters, and presence of an output schema, the description covers everything an agent needs: what it returns, when to use it, and the empty-string sentinel. No critical information appears 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 100%, so parameters are already documented. The description adds value by explaining that sender and subject are used to find 'similar' past contexts, giving the parameters meaningful filtering semantics beyond their raw schema definitions.

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?

The description clearly states that the tool returns learned patterns from past user corrections for similar senders/subjects, intended as drafting context. It is specific about the resource and output, though it does not explicitly contrast itself with siblings like sender_history.

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 description says to use it when drafting, with the returned text block meant to be placed into drafting context. It implies the sender and subject parameters are the basis for similarity matching, but it does not explicitly describe when not to use it or name alternatives.

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