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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), yet the description adds genuinely new context: the token budget ('under 1k tokens'), paging behavior, the audit-checklist side effect, and 'No confirmation needed.' These go beyond what structured fields declare.

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?

Front-loaded with the core purpose, then a compact per-view breakdown, then usage. Dense but every clause carries information; slightly long, but no filler sentences.

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, return-value explanation is unnecessary, and the description covers view semantics, usage timing, and confirmation behavior. Complete for a read-only inspection tool; minor absence of explicit sibling routing keeps it from a 5.

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 baseline is 3, but the description adds real meaning beyond the schema: atlas returns the whole system in under 1k tokens, purpose=audit appends a checklist, and related accepts item_ids/titles/files/query as seeds. This clarifies the intent of enum and parameter choices.

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 (this workspace's memories, rules and skills) and the exact operation (read-only map grouped into regions), then breaks down all three view modes with what each returns. An agent can distinguish this from siblings like list_memories, read_memory, or get_tree without opening those schemas.

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?

Gives clear timing context: 'Use before a quality pass, before updating knowledge, or to see how things relate.' The related view also implies routing ('what else to read or update'). It stops short of naming a sibling alternative with an explicit when-not condition, so it is strong but not exhaustive.

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