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

Beyond the annotations, it discloses the required permission scope (settings:write with the exact consent string), the sign-in requirement when the member has not connected, the per-member cap of 20 saved searches and that refusals are surfaced, that creation is unconfirmed and reversible in one step, privacy boundaries, and where the result is recorded (Settings → Connected agents). It also repeats the write/non-destructive profile consistently with readOnlyHint=false and destructiveHint=false.

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?

Information-dense and front-loaded, but rendered as one long chain of parentheticals that is harder to scan than it needs to be, and some clauses are idiosyncratic padding ('the door's own refusal is passed on', the final prompt-injection boilerplate). Nearly every sentence carries content, yet the packaging costs readability for an agent parsing it quickly.

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 9-parameter write tool with no output schema, the description covers authorization, defaults, quota, reversibility, return path and consent language. An agent has everything needed to call it correctly and to know what happens on failure.

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 only 33%, so the description must carry the load and largely does: it names the searchType domains, query, location/state/skills, occupation, the name fallback behavior, the alertsOn default, and the instant/daily/weekly alert cadence. Only occupationId's lookup dependency is left to the schema rather than restated, and name/alertFrequency formats are implied rather than spelled out.

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 (save a search) plus the secondary effect (alert them to new matches), then enumerates the exact content of a saved search: searchType values, query, location/state/skills/occupation, name, and alert settings. An agent can distinguish this from edit_saved_search, delete_saved_search and list_my_saved_searches without opening a 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?

Gives concrete when-to-use framing by anchoring to the product surface ('The Save Search button on search results'), and supplies defaults that decide behavior (name auto-derived when omitted, alerts on unless alertsOn false). It implies a read-back path ('Read back') but never explicitly names list_my_saved_searches or edit_saved_search as the follow-up alternatives, so routing is clear but not exhaustive.

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