memory_search

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

With only readOnlyHint=true supplied, the description usefully discloses the return shape (#id, kind, date, short text), which compensates for the absent output schema. It does not mention relevance ranking, result ordering, or how limit interacts with multiple results, but the core read behavior is clear.

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?

Two compact clauses, front-loaded with what is searched and followed by what comes back plus the natural follow-up call. No filler or redundancy.

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?

The description covers the core search-and-fetch loop and the return fields, which is the most important information for a read-only search tool. But for a 10-parameter tool it omits the multi-query 'queries' feature, include_history semantics, and the detail level, leaving meaningful behavior unexplained.

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 only 50% across 10 parameters, and the description explains none of the undocumented ones: query, kind, tags, detail, and include_history have no meaning added beyond their names. Given the low coverage, the description should be compensating and instead adds nothing about filtering or history behavior.

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 ('Search saved notes') and enumerates the content kinds it covers (decisions, preferences, facts). It also distinguishes itself from memory_get by declaring that get returns the full note, though it says nothing about memory_list or memory_related.

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?

The mention that 'memory_get(id) gives the full note' implies a search-then-fetch workflow, which is useful context. However, there is no explicit guidance on when to use this versus memory_list or memory_related, and no statement about when not to search.

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