Save a revenue insight

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description is consistent with that and adds a genuinely non-obvious behavior: 'Saving an existing key keeps the previous value in its history,' i.e. it is an upsert with retained history. It does not cover return values or whether confidence/memoryType affect merging, leaving some gap.

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?

It is front-loaded with the action and the trigger condition, and every clause adds information. The single long sentence with stacked colons is slightly unwieldy, which costs it a point.

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 6-parameter write tool with full schema coverage, no output schema, and annotations covering the safety profile, the description covers what to save, when to save, and key-reuse behavior. The one notable omission is what the tool returns (e.g., the stored memory id/history reference), which would help an agent confirm the write.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema by tying the key parameter to upsert/history behavior, which the schema does not say. Nothing is said about confidence or memoryType semantics beyond the enum descriptions already provided.

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 uses a concrete verb+resource ('Writing down what each deal taught' → saving a revenue insight) and enumerates the kinds of content it holds: deal decisions, win/loss reasons, ICP refinements, metric updates, strategic pivots. An agent can distinguish this from get_revenue_memory by the verb alone, though the description never names that sibling explicitly.

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?

It gives an explicit trigger: 'use this when the person asks you to remember something about their revenue,' followed by concrete example cases that map to the category enum. There are no exclusion conditions or named alternatives, so it falls short of a 5.

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