Search memory

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the default scope filter, the fact that archived scope surfaces previous versions, and that results carry memory_at and a history_id that is null for current entries. It stops short of describing result ordering or paging behavior, so it is not a 5.

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 dense sentences, zero filler, and the most decision-relevant facts (what is searched, default scope, scope variants) are front-loaded ahead of the sibling routing and the playbook_id note.

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 12-parameter, no-output-schema search tool, the description covers the discriminating behavior (scope semantics, result fields, alternative tools) well. It omits result ordering and how search matching is done (the schema says 'literal text'), which are minor gaps rather than blockers for correct invocation.

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 100%, so all 12 parameters are already documented, including the scope enum and playbook_id. The description's prose about scope and playbook_id restates rather than extends the schema; the extra return-field note (memory_at, history_id) is output information, not parameter semantics. Baseline 3 is correct.

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?

The description opens with a specific verb and the exact fields searched ('keys, JSON values, descriptions and summaries'), and its scope semantics ('archived searches archived entries and previous versions') clearly separate it from siblings like get_memory_history and read_memory. An agent can distinguish it from the other memory tools 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 states the default behavior ('Defaults to current, non-archived memories'), defines what each scope value does, and routes the agent to explicit alternatives with the condition that selects them: get_memory_history for one key's prior versions, read_memory for its current value. That is the full when/when-not/alternatives triad.

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