check_saved_search

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

With no annotations present, the description carries the full burden and does disclose the key non-obvious trait: mark_seen=True persists returned IDs as seen, mutating state that affects subsequent calls, and False gives a dry-run. It omits any note on permissions or what happens to deleted/expired saved searches, but the critical side effect is surfaced.

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?

One sentence of purpose followed by a compact Args block; every line earns its place and the core behavior is front-loaded. Slightly verbose line-wrapping on mark_seen, but no waste.

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 the description rightly does not explain return values. It covers the tool's novelty filter and state-mutation semantics; the only gap is routing guidance relative to similar siblings (check_new_matches, run_hunt).

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, documenting both required 'name' and the optional 'mark_seen' with its default and exact behavioral consequence. Nothing beyond what's stated is needed to call it correctly.

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?

Specific verb+resource: 'Re-run a saved search and return only listings not seen before' — an agent immediately knows it re-executes a stored search with a novelty filter. It does not, however, distinguish itself from the sibling check_new_matches, which sounds like it could serve a similar role.

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?

Usage is implied rather than stated: the tool presumes a saved search already exists (created via save_search). The description gives one conditional instruction ('Set False for a dry-run') but never says when to prefer this over check_new_matches, run_hunt, or search_listings.

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