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

Annotations only declare readOnly=false, destructive=false, openWorld=true. The description adds substantively more: notifications arrive by email or push, live or as a summary, the call proceeds without confirmation, it affects no one else, it is reversible via delete_saved_search, and it requires a Cotlet API key scoped to this app. That is exactly the mutation/blast-radius context the annotations do not carry.

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 purpose followed by returns, notification behavior, security/reversibility, and auth in four tight sentences. There is minor redundancy between 'Save a search' and 'Creates a saved search', but nothing wasteful enough to impede scanning.

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 4-param mutation with no output schema, the description covers what is created, what is returned (current match count), how alerts are delivered, that it is reversible, and the auth requirement. An agent has everything needed to call it and set expectations correctly.

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 100%, so location, filters, frequency and notify_by are already documented with enums and defaults. The description echoes the notification channel and cadence ('email or push, live or as a summary') but adds no syntax, format, or filter-composition detail beyond the schema, so the baseline 3 applies.

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 (save/create) plus resource (saved search) plus the side effect (notifications about matching homes) and the immediate return (count of current matches). It also names the sibling delete_saved_search, so an agent can separate it from list_saved_searches or search_listings 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?

The description implies the trigger (when the user wants a standing search with alerts) and explicitly notes it runs without asking and is undone by delete_saved_search in one call, which is real routing context. It stops short of stating when NOT to use it versus list_saved_searches or search_listings, so it is clear context without explicit exclusions.

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