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

Beyond the annotations (readOnly=false, destructive=false), the description discloses the critical replacement semantics ('filters REPLACE the saved filters entirely'), that omitted keys are kept, that Telegram notifications fire when alerts are on, and the concrete rate limits (30/hr storage edits, 20/hr feed edits). These are exactly the operational facts an agent needs and cannot infer from the schema.

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 description is dense but front-loaded: verb and fields first, then the replacement hazard, then the confirmation rule, then the rate limits. Every sentence carries an operational rule, though the final rate-limit sentence is compressed enough to require careful parsing.

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 7-parameter mutation with nested filter objects, the description covers the risky behavior (replacement), confirmation policy, and cost model well. Since no output schema exists, the description does not say what an update returns or how to verify the change, which is the one remaining 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 already 86%, yet the description still adds real meaning: filters must be sent whole rather than as a patch, ai_filter with an empty string removes it, agent_notes-only edits bill as a storage change, and user_confirmed is conditional on explicit user approval. run_id and its tuner-specific constraints are left entirely to 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?

The description opens with a specific verb and resource ('Change a feed') and enumerates the mutable fields (name, filters, ai_filter, agent_notes), which is enough to distinguish it from create_feed/delete_feed. It never explicitly names those siblings, so it stops short of a 5.

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?

It gives concrete when-to-use rules: pass user_confirmed only after showing the user the change when alerts are on, while an alerts-off feed or agent_notes-only edit needs no confirmation. It also routes the agent to list_feeds for the current filters. No guidance on when to prefer an alternative sibling (e.g., delete_feed, set_feed_alerts) for related operations.

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