save_search

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

With no annotations, the description carries the full burden, and it discloses a genuinely non-obvious state trait: seen_ids starts empty, so the first check_saved_search backfills all current matches, plus the workaround to suppress it. It omits idempotency/overwrite behavior on duplicate names and any auth or rate-limit context.

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 purpose leads, followed by per-argument notes and the one non-obvious behavioral caveat. Every sentence carries information an agent needs; nothing is restated from the schema.

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?

An output schema exists, so return values are covered elsewhere, and the description adds the creation-time semantics that matter for correct invocation. Only the duplicate-name/overwrite contract and prerequisite for the delegated 'params' shape are missing.

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, and it does: it gives the name format ('trek-bike-antwerp'), states that params mirrors search_listings kwargs, and flags the required 'site' key. It still leaves the full param vocabulary to the agent's knowledge of search_listings rather than enumerating it.

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?

States a specific verb and resource ('Persist a search') and immediately names the sibling that consumes it ('re-run via check_saved_search'). An agent can distinguish this from search_listings (transient) and list_saved_searches without opening any 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?

Clearly establishes the use case (persist for later re-running) and links the required params to search_listings, giving the agent a concrete pattern to follow. It does not state exclusions (e.g., when to prefer save_hunt instead) or whether an existing name errors versus overwrites.

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