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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered structurally. The description's only added behavioral signal is the word "active," weakly implying forgotten or archived memories are excluded, but it never says so explicitly or explains result ranking, scope boundaries, or cross-tenant isolation.

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 short sentence is maximally front-loaded and free of waste, but at this length the brevity reflects under-specification rather than disciplined concision. It earns no penalty for padding, yet the one clause it does contain is vague.

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 4-parameter search tool with half its schema undocumented and no output schema, the description leaves major gaps: no explanation of what is searched, what a result looks like, how limit defaults, or how to page. Annotations cover safety but not semantics, so an agent would have to guess at call behavior.

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 description coverage is 50%: kinds and share are documented in the schema, while query and limit have no documentation anywhere. The description adds nothing about any parameter, so it does not compensate for the two undocumented fields or clarify what query matching semantics apply.

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?

"Search the tenant's active memory" gives a specific verb (search) and resource (memory), which is more than tautology. But "active memory" is never defined, and nothing distinguishes this from siblings like memory_evidence, memory_expand, or memory_turn_context, all of which plausibly surface stored memory too.

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?

There is no when-to-use guidance, no trigger conditions, and no mention of any alternative tool. An agent cannot tell from the description whether this is the entry point for recall or a narrow lookup, nor when to prefer memory_expand or memory_turn_context instead.

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