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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds useful downstream context — the content engine reads saved text when it writes. However, it doesn't address the practical consequences of idempotentHint=false (e.g., whether repeated saves accumulate duplicates) or what persistence/reversibility looks like, so it adds moderate value rather than rich detail.

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, front-loaded with the core purpose and followed by the usage trigger. The example list is a bit long but each item clarifies scope rather than padding.

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 one-parameter write tool with no output schema, the description covers purpose, trigger, and downstream effect. The only mild gap is not clarifying whether repeated saves append or overwrite, which matters given the non-idempotent annotation.

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?

With a single parameter at 100% schema coverage, the schema already documents 'text' as 'What to remember, in the user's own words.' The description goes beyond that by enumerating the kinds of content worth saving, which meaningfully guides what to put in the parameter.

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 gives a specific verb ('Save') plus the resource ('something about the business that the crawl cannot see') and concrete examples of what qualifies (buyer identity, product limitations, positioning decisions). This is clearly distinguishable from siblings like add_competitor, generate, or track_question.

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 states an explicit trigger: 'Use this whenever the user explains something about their business in conversation that the product would otherwise be guessing at.' That tells the agent both the when and the rationale, though it names no alternative tool or explicit when-not condition.

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