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

Annotations only provide readOnlyHint=false; the description adds substantial behavioral context: the tracker is created in the user's brain, runs daily, emails new matches filtered by the prompt, and returns a page_url where the user can review, edit, and Run Now. No contradiction with 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?

The description is longer than minimal but each part earns its place: examples, parameter mapping, runtime behavior, and the page_url instruction. The phrase 'in their brain' is slightly redundant/colloquial, which keeps it from top marks.

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?

With no output schema, the description still covers the key return value — page_url — and what the user can do with it. Required params, optional enum choices, filtering behavior, and scheduling are all described well enough for correct invocation.

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%, but the description adds real value beyond the schema: it maps tracker_type to user phrasing (tweets/X, Google results, URL), explains that a URL to watch means web_page with query as a short label, and clarifies that prompt is stored and later applied as a filter.

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 clearly identifies a specific action: setting up a standing search or tracker. Concrete examples like 'track LinkedIn posts that mention hubspot' and 'watch acme.com/pricing for changes' distinguish this from one-off search and read tools among the siblings.

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 clearly states when to use it: whenever the user wants a standing search watched, with relatable examples. It does not explicitly say when not to use it or contrast with one-off search tools like search_slack_messages or get_my_linkedin_posts, so it stops short of a 5.

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