search_product_memory

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

With no annotations, the description carries the burden and does well: it states the tool returns snippets plus `store_path`, explains the cost tradeoff of `full=True` ('costs roughly five times as much'), and implies read-only behavior through 'search' and 'returns.' It does not detail rate limits or authorization, but for a search tool the key behavioral aspects (output format, performance) are covered.

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?

The description is compact (about 60 words), front-loaded with the core purpose, and each subsequent sentence adds vital operational detail (return format, follow-up action, cost tradeoff). There is no filler or repeated schema information.

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?

Despite the lack of parameter descriptions and annotations, the description covers the essential agent workflow: search by query, inspect snippets, read a file when relevant, or request full bodies at a known cost. The presence of an output schema excuses deeper return-value detail, but the intended meaning of project/repository filters remains under-specified.

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 0%, so the description must compensate. It explains the `full` parameter meaningfully (snippets vs. whole bodies, cost), but `query`, `limit`, `project`, and `repository` receive no elaboration—their meanings are left to inference from names and types. The description adds some semantic value but leaves significant gaps for filtering parameters.

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 'Ranked search over all verified product/architecture/incident memory,' naming a specific verb (search), a distinct resource (verified memory), and a clear scope. This differentiates it from siblings like read_memory (which reads files by path rather than searching content) without needing to reference them explicitly.

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 description gives actionable workflow guidance: 'Read the file when a snippet turns out to be the thing' and explains when to use `full=True` versus scanning snippets. This effectively contrasts the tool with file-read alternatives, though it does not explicitly discuss when to prefer search_product_memory over other sibling search-like tools such as get_related_decisions.

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