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

With no annotations, the description carries the full burden. It discloses pagination behavior ('Cursor pagination, maximum 100 results') and a meaningful privacy guarantee ('Your memory vault stays private'). However, it doesn't explicitly confirm read-only semantics, result ordering, or error/edge behavior that an agent would want for an unannotated search tool.

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?

Four sentences, each earning its place: purpose, parameter usage guidance, pagination constraint, and privacy scope. Purpose is front-loaded with zero filler or repetition of schema content.

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 an 8-parameter tool with no annotations and no output schema, the description covers the core use case and privacy scope well. But it leaves notable gaps: no return format, unclear after/before cursor mechanics, and unspecified metadata filter shape — all of which the agent cannot infer from the minimal schema.

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 only 38%, so the description must compensate. It partially does: it explains the mentioned parameter's two modes, implies metadata is searchable via 'search text and metadata', and caps limit at 100. But after/before are only generically covered by 'cursor pagination' with no mapping to the cursor fields, and metadata filter semantics remain vague.

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 description gives a clear verb and resource ('Retrieve channel context or search text and metadata') and clarifies the two modes of operation via the mentioned=true guidance. It is distinguishable from siblings like message_send, though it doesn't explicitly name an alternative or differentiate from context_get.

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?

Provides concrete decision guidance: 'Use mentioned=true for your mentions; omit it when pulling the full conversation around a mention' plus a pagination cap of 100 results. It doesn't name alternative tools or state when not to use this tool, but the scenario-specific instruction is actionable and valuable.

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