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

Annotations only say not-read-only, non-destructive, closed-world; the description adds genuinely new behavior: append-only semantics, deduplication that returns the existing record with deduplicated=true, self-scoped writes, and undo from the same surface. The only gap is that it never describes the shape of the returned record beyond the deduplication flag.

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?

Front-loads the core action and the append-only/dedup rules in the first two sentences, then alternatives, then confirmation policy. Dense but well ordered; the trailing 'everything destructive, outbound or financial still proposes' line is general policy that is not strictly about this tool, mildly inflating length.

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 append-only write tool with no output schema, the definition covers purpose, alternatives, mutation semantics, dedup return, and confirmation behavior. The remaining hole is parameter-level detail for tags and content formatting, which matters because the schema documents neither.

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 meaning of both parameters. It implies what 'content' is (a fact to recall) but says nothing about the 'tags' array — format, casing, or whether tags affect deduplication — leaving a documented-in-neither field.

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 resource ('store a long-term memory fact ... in their active workspace') and frames it as forward-looking recall material. It explicitly distinguishes itself from update_memory for corrections and recall_memory/search_personal for retrieval, so an agent can place it among siblings without opening a schema.

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?

Gives explicit routing: use update_memory to correct a fact, use recall_memory/search_personal to read it back, and this tool for storing new facts. It also resolves the biggest ambiguity for an agent — whether to propose-and-wait — by stating the write runs immediately and needs no plan_token.

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