Build context

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: what `compact` strips, that `depth` bounds traversal at 5 hops, and that `since` narrows related results. It does not discuss pagination behavior across primary vs related results, which is left to the schema.

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 tight sentences: traversal scope first, then the identifier contract, then the time filter, then the compact/read split. Every sentence carries operative information and none repeats the tool title back at the reader.

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?

An output schema exists, so return shape need not be described. Required input is a single identifier, which is fully specified, and the highest-leverage optional knobs (depth, since, compact) are explained. The remaining params are low-risk tuning values documented in the schema at 89% coverage.

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 89%, so the baseline is 3; the description goes further by enumerating the identifier formats (path, permalink, memory:// URL, glob pattern), clarifying that `since` applies to related results rather than the root note, and explaining the practical consequence of `compact`. Page, page_size, max_related and project are left to the schema, which is acceptable at this coverage.

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: follow the Basic Memory knowledge graph from a note, returning the note, its observations, and notes reached by relations up to `depth` hops. It also distinguishes itself from bm_read by naming that sibling as the way to read full note bodies, so an agent can tell the two apart without opening a schema.

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 clear context for use (graph traversal from a starting note, with `compact` for a body-free view) and explicitly routes follow-up reading to bm_read. It does not state when NOT to use this versus search_notes or bm_search, so it falls short of a full when/when-not/alternative treatment.

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