brief

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

With no annotations, the description supplies key behavioral facts: the tool is a one-time load at session start, returns a project-context snapshot including stale entries, and results remain valid for the whole conversation. It doesn't explicitly state read-only semantics or failure modes, but 'load context' implies non-destructive behavior and the cached-results disclosure adds value.

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 sentences carry the essential call timing, return values, example, and validity window. Minor redundancy between 'Start of conversation' and 'Call once at session start' prevents a 5, but it remains tight and well organized.

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 simple one-optional-parameter tool with no output schema, the description covers main return categories, call timing, and validity. However, it doesn't explain behavior when lobe is omitted (required list is empty) or the memory_bootstrap prerequisite beyond the schema property text, leaving a small but meaningful gap.

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?

The input schema already describes 'lobe' as a memory lobe name and even provides prerequisite bootstrap guidance, so schema coverage is complete. The tool description contributes a concrete example ('lobe': 'my-project') but no additional meaning beyond the schema, matching the baseline of 3.

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 clearly identifies the tool as a session-start context loader with a specific resource ('context for a project') and enumerates the returned content (preferences, gotchas overview, stale entries, counts). It distinguishes itself by covering everything saved via learn/gotcha/convention/prefer, but doesn't explicitly contrast with sibling tools like recall or gotchas.

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?

It gives explicit timing guidance: 'Call once at session start' and 'no need to re-call,' which tells the agent when to use it. It doesn't name alternatives or exclusions, so it stops short of a 5.

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