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

Annotations only say readOnly=false, destructive=false, openWorld=false; the description adds substantially more — re-rating replaces the earlier rating, and it counts as a storage change with a 30/hour budget. That mutation and rate-limit context is exactly what an agent needs and is not in the annotations.

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?

Front-loaded with the verb and resource, and nearly every clause carries a constraint or disambiguation that earns its place. It is one dense run-on block though, so the parameter guidance would be easier to scan if separated from the usage rules.

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 mutation tool with no output schema, it covers everything: what gets stored, replacement behavior, rate limits, provenance of feed_id and job, and the conditional requirement on reason. Nothing an agent needs in order to call it correctly is 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?

Adds real meaning beyond the 80%-covered schema: where feed_id must come from (matched_feeds in find_jobs or the alert's feed), that job is the upwork_id, the semantics of each reason enum value (skill/budget/client/other), and that note should be the user's own words. The enum meanings appear nowhere in the schema.

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 — recording the user's own thumbs up/down on one job — and immediately names the equivalent UI affordance (the buttons under a Telegram alert) plus what consumes the signal (offer/feed tuner). This clearly separates it from siblings like find_jobs, get_job_details, and set_feed_tuner.

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 explicit when-to-use conditions (only when the user stated their opinion in their own words), explicit when-not (never from the agent's own judgement — route that to agent_notes; never in bulk), and a concrete exclusion (jobs from find_jobs with ad hoc filters have no feed and must not be rated).

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