Context

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value by enumerating what content is returned (CLAUDE.md rules, Home, topic-relevant notes), but says nothing about volume, ranking of 'relevant' notes, or cost of the call.

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; the bundle contents are enumerated immediately after the framing purpose.

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 an output schema present, the description need not explain return shape, and it correctly focuses on what gets bundled. For a read-only, single-optional-param tool this is close to sufficient, with only the 'relevance' selection logic left implicit.

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% and there is only one optional parameter with a documented default, so the schema carries the semantics. The phrase 'notes relevant to a topic' loosely ties the topic param to retrieval relevance, but adds no format or scoping detail beyond the 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?

States a specific resource bundle (vault rules/CLAUDE.md, Home, topic-relevant notes) framed as start-of-session context, which is more precise than the bare name 'context'. It distinguishes itself from generic siblings like search/read by being an aggregate bootstrap fetch, though it never names those alternatives explicitly.

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?

'Start-of-session' implies the usage moment, so an agent can infer this is a bootstrap call rather than an on-demand lookup. However, it gives no explicit when-not guidance and does not name search/read/people_graph as the alternatives for mid-session or targeted retrieval.

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