Recommend for this work

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description does add genuine behavioral context: the result is a shortlist, each item carries a one-line `why` and a score, and packs are surfaced via `ownedOf`. It does not mention ranking quality, latency, or whether prices/availability are live, but for a read-only recommendation call that is a reasonable level of disclosure.

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?

Dense but front-loaded: the purpose lands in sentence one, then the input constraints, then the result shape, then the follow-up flow. The phrase 'then recommend with your own reasons' inside the recommend tool's own description is slightly circular and could be tightened, but no sentence is filler.

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?

With six parameters, no output schema and only read-only annotations, the description carries the burden well by describing the return payload (why, score, packs, ownedOf) and the shortlist limitation. The remaining gaps are minor: no pagination or truncation behavior for `limit`, and no signal about ranking confidence.

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 100%, so the baseline is 3, and the description earns an extra point by telling the agent what to put in `context` (plain lines about the project plus the person's request) and what must never go in it (file contents, secrets, personal data). It also implicitly connects `includeOwned`/`packs`/`ownedOf`, which the schema alone does not tie together.

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?

'Products that fit what the person is working on' states the resource and the matching basis clearly, and the closing 'this only shortlists' scopes the output. It is distinguishable from search_products by being context-driven rather than query-driven, though it never names the sibling directly.

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 prescribes a concrete workflow: feed in project_summary's `text` plus the person's request, then read get_product for the best few and present with your own reasons. What is missing is an explicit negative rule (when to prefer search_products or list_shelves instead), so it falls short of full when/when-not coverage.

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