Remember

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

With readOnlyHint=false and idempotentHint=true already declared, the description adds real behavioral value by explaining the merge/reinforce semantics for near-duplicates, which is exactly why the operation is idempotent. It does not say what permission or rate limits apply, but the added write-behavior context exceeds the annotations.

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 short sentences, front-loaded with the core action and scope, then categories, then the dedup contract. No filler and no repetition of the title or name.

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 no output schema, it covers purpose, content-writing guidance, and the merge contract. The one gap is that it never explains how an agent obtains the id needed by link_to, nor what the call returns.

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 a 3, but the description adds meaning for the content parameter ('write it self-contained, as if read months later without this chat'), which is guidance the schema does not provide. The other five parameters are left entirely to their schema descriptions.

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 one durable fact') plus the scope ('available in future sessions'). It is clearly distinguishable from the sibling store/retrieve tools (recall, forget, reinforce) without opening any 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 content categories to use it for (decisions and reasons, preferences, project facts, commands, gotchas, fixes) and a writing rule. It does not name the alternative tools or the when-not conditions (e.g., use forget to retract, recall to read), so it stops short of a full routing guide.

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