memory

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

With no annotations at all, the description must carry the full behavioral burden. 'Read' and 'search' imply a safe read, but nothing states whether results are scoped, paginated, ordered, or what an empty/ambiguous site value does, and there is no output schema to fall back on.

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 front-loaded sentence with no filler. It is efficient, though the terseness comes at the cost of the missing detail rather than being a virtue of restraint.

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?

Three optional parameters, zero schema documentation, no annotations, and no output schema — the description should do substantially more. An agent can guess a path forward but cannot predict which mode it will trigger or what comes back.

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%, so the description must compensate and it does not. It implies 'site' is an identifier and 'search' is a query string, but adds no format, matching semantics, or interaction rules, and the 'profile' parameter is completely unaddressed.

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?

Names two operations (read site notes, search all local notes) against the resource 'memory', which gives an agent a rough idea. However, it never explains what a 'note' or 'site note' actually is, and the third parameter (profile) has no corresponding purpose in the description, so the tool's full scope stays vague.

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?

'or' hints at two modes but gives no conditions for choosing between them (e.g. what happens when both site and search are supplied, or when neither is). No mention of the obvious sibling 'remember' (written by contrast), so an agent gets no routing guidance for the read/write split.

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