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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds real behavioral context beyond that: outbound Telegram notifications per matching job, the ai_filter being applied before each notification, and the user_confirmation gate. It does not say what happens on duplicate feeds or how the feed is later modified/removed (update_feed/delete_feed exist), which keeps it out of 5 territory.

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 definition, then routing guidance, then the confirmation protocol; every sentence carries instruction. The confirmation point is restated ('ask first... never assume' appears in both description and user_confirmed schema text), which is mildly redundant but defensible given the stakes.

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?

A mutation tool with nested filter objects and no output schema, so the description must carry the load — and it covers creation semantics, the confirmation gate, filter completeness, and the AI-filter role. It omits any indication of what is returned (e.g. a feed id) or how the new feed relates to existing ones, a minor gap.

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 baseline would be 3, but the description adds a constraint the schema does not enforce: 'Takes complete filters (base.q is required)' — the schema only marks schema_version as required inside filters. It also flags ai_filter as the channel for criteria structured filters cannot express, which clarifies intent beyond the schema text.

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+resource and defines the concept inline ('a feed: a saved search in the Telegram bot that sends the user a Telegram notification about every new matching job'). It also explicitly distinguishes itself from find_jobs, so an agent can route without opening either 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?

Explicitly says when-not to use it ('NOT needed to search or monitor jobs here: use find_jobs with filters') and names the alternative, then adds a hard precondition with a concrete counterexample ('"I want jobs about X" is not such a confirmation'). This is a complete when/when-not/alternatives statement.

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