remember

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

With no annotations, the description carries the full burden. 'Append' hints at a write, but it never says whether entries are deduplicated, whether 'local' means per-machine or per-profile, whether writes are reversible, or what permaleness/visibility the stored note has.

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?

A single short sentence with no wasted words and the key verb front-loaded, but the brevity comes from under-specification rather than economy. Nothing is structurally wrong; there is simply too little there.

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 3-required-parameter write tool with no annotations and no output schema, the description supplies nothing about inputs, persistence semantics, or return behavior. An agent cannot call this correctly without trial and error.

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 0% and there are three required parameters (profile, site, text) that the description never explains. At best 'site' is echoed by the word 'site'; the meaning and expected format of 'profile' and 'text' are left entirely undocumented, which is below the compensation bar for a low-coverage schema.

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 fragment 'Append local site know-how' gives a verb (append) and a vague resource ('site know-how'), but never says what a memory entry actually is or what gets persisted. Against a sibling literally named 'memory', an agent cannot tell these two persistence tools apart from the description.

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?

There is no statement of when to use this instead of 'memory', 'snap', or other siblings, and no prerequisites or exclusions. The agent must guess the trigger condition entirely.

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