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

Annotations already declare read-only, idempotent, non-destructive, but the description adds behaviour the annotations cannot: nothing is saved until the user confirms, at most one e-mail per day, and one-click unsubscribe. It also discloses the hand-off point (the user acts on the linked page), which is decisive for correct agent behaviour.

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 "Read-only." and then the core return value, followed by operational constraints in short clauses. Every sentence carries either behaviour, workflow, or a constraint; nothing is repeated from the annotations or schema.

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?

An output schema exists, so the return value need not be explained in detail, and the description still says what the link leads to and what happens after the user follows it. For a single nested parameter tool, the agents' remaining questions (when, what criteria, who supplies the e-mail, what persists) are all answered.

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 the baseline is 3 and the nested criteria object is fully self-documented. The description nevertheless adds cross-tool semantics (same criteria as search_listings) and the at-least-one constraint, though it does not restate the individual fields, which is appropriate.

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 (returns a link to a page on objelio.de where the user can subscribe to e-mail alerts for the given criteria) and immediately identifies what the link is for, which no sibling tool does. An agent can distinguish it from search_listings, get_listing, or explain_criteria without opening the 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 instructs to pass the same criteria as search_listings with at least one criterion, and gives the alternative workflow constraint: the user enters the e-mail address on that page and confirms it by e-mail, so the agent should not ask for it in chat. That is both when-to-use and an explicit don't-do, which is rare and valuable.

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