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

With annotations present (readOnlyHint=false, destructiveHint=false), the description still adds real behavioral value: the extraction pipeline, filler discarding, near-duplicate merging, and the important note that a skipped result is normal rather than an error. The only gap is what happens to the existing memory when a merge occurs.

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 tight sentences with the core action front-loaded and the non-obvious pipeline behavior immediately after. No filler, no repetition of the schema.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the surprising result case (skipped is normal). What is missing is what a successful merge does to the prior memory and whether repeated identical calls are safe, which matters given idempotentHint=false.

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 all three parameters (text, source, metadata) are already documented in the schema. The description adds no syntax, format, or content examples for 'text' beyond what the schema states, so the baseline of 3 applies.

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 with scope: 'Store a durable fact or preference about the user.' An agent can distinguish this from delete_* and get_* siblings on the write/read axis, but the description never names the closest alternative (update_memory) to make the add-vs-update boundary explicit.

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?

Usage is implied by the verb 'store' and by the note that near-duplicates are merged, which hints this is for new facts rather than edits. However, there is no explicit when-to-use guidance, no mention of when to prefer update_memory, and no prerequisites stated.

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