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

Annotations declare destructiveHint=false and openWorldHint=false but readOnlyHint=false, so the description carries the burden of explaining the non-read side effect: refresh runs a fresh observation pass against current platform state. It also discloses real prerequisites — Max must be MCP-enabled by an owner plus the user's stored consent — which is exactly the kind of gating context annotations cannot convey. It stops short of saying what happens when consent is missing or how long a fresh pass takes.

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 front-loaded sentences ordered by value: what it returns, the refresh mode, then prerequisites. The only fat is the branding clause 'the platform's always-on companion', which does no selection work.

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?

With no output schema, the description does the necessary job of describing the return ('pending and recent proactive notes'), covers the mutate-ish refresh mode, and names the consent/enablement gate. Remaining gaps — note shape, latency of a fresh pass, and failure mode when Max is disabled — are modest for a two-optional-parameter tool.

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 3. The description still adds meaning beyond the schema for `refresh`, clarifying that it evaluates current platform state and only produces a note when warranted, whereas the schema merely says 'run a fresh observation pass'. The `context` parameter is left entirely to its own verbose schema text, which is acceptable.

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 — returns pending and recent proactive notes from Max — and scopes the content to projects, test runs, and crawls. The `refresh=true` variant is described as a distinct mode, so an agent can distinguish this from read-only sibling inspection tools like get_project_memory or get_project_summary.

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?

Clear context for when to call: to fetch queued proactive notes, and optionally to force a fresh pass. It even conditions the refresh on 'something genuinely worth saying', which signals the call may legitimately yield nothing. No sibling alternative is named explicitly, which keeps it 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.