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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds behavior those annotations cannot express: result ordering driven by the time field, order:'oldest' for timelines, and that ambiguous/missing ID prefixes surface in errors[] rather than being silently dropped. It stops short of describing pagination or result shape, but the error-reporting and ordering disclosures are genuinely useful.

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 verb and filter list, then progressively adds intersection rules, ordering, and the routing alternative. It is dense and slightly long, but each sentence carries non-obvious information (timestamp independence, error reporting), so little is wasted.

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 6-param, 0-required tool with nested tag/time objects and no output schema, the description covers the semantics an agent needs to build valid multi-clause queries plus ordering and error behavior. Remaining gaps (result shape, limit interaction) are minor and partly covered by the schema.

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 67%, and the description compensates with semantics the schema does not carry: all provided clauses are intersected, a time clause alone is valid and answered from each memory's own timestamp rather than date tags, and IDs accept full UUIDs or unique 8-char prefixes. It does not restate limit bounds or the project fallback, which the schema already documents.

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+resource (query memories) and enumerates the exact filter composition it supports: IDs, OR-tag, AND-tag, exclusion, date range, with intersection semantics. It also distinguishes itself from the sibling muninn_memory_search (topic-inside-range) and from muninn_memory_list_by_tag, so an agent can route 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?

Explicitly names when to use it (bundle content audits, convention checks, any multi-condition fetch) and, more importantly, names the alternative and the condition that selects it: 'For a topic inside a date range, use muninn_memory_search with time.' That is exactly the when/when-not/alternative guidance the dimension asks for.

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