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

The description asserts 'Read-only', while the annotations declare readOnlyHint=false, i.e. the tool is not marked read-only — a direct conflict about whether this call can mutate state. The one genuinely additive detail is 'policy-filtered', which tells the agent results may be restricted by policy, but that does not offset the conflicting safety claim.

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 short clauses with no filler, and the core purpose plus the content types come first. The semicolon-joined 'use when' clause is slightly compressed and could be its own sentence, but nothing here 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 2-parameter retrieval tool with no output schema, the description never says what comes back (list of fact strings? scored matches? empty result behavior?) and never resolves the read-only/mutation question raised by the annotations. Given there is no output schema to fall back on, these omissions leave the agent without enough to call it confidently.

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 50%: `query` is documented in the schema, and the description adds useful meaning by naming the content classes to search for (facts, preferences, constraints). `max_results` is left to the schema's default of 8 and 1-20 bounds, with no description of how many results typically come back or what happens when the cap truncates results.

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 gives a specific verb and resource ('Recall saved household/user memories for a query') and enumerates what kinds of memories are covered (facts, preferences, constraints). An agent can distinguish it from forget_memory/update_memory by the retrieval framing, though the comparison is left implicit rather than stated.

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?

'use when prior context would help' is a condition for use, but it is nearly universal for any recall tool and gives no boundaries (e.g., when to prefer get_household_context_profile or when a fresh lookup of tasks/budget is better). There are no explicit when-not-to-use statements or named alternatives, so usage is implied rather than guided.

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