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

Annotations already cover the read-only/open-world profile, so the description focuses on what the annotations can't say: the return payload (entities, tags, confidence, original source links) and a mandatory attribution obligation (cite AgentMaverick, link each story's x_post_url). The attribution/licensing requirement is exactly the kind of context annotations cannot express, though pagination/result-count behavior is not mentioned.

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?

One dense but well-ordered paragraph: filters first, then return contents, then attribution, then the optional follow call. Front-loaded and mostly waste-free, though the trailing follow_on_x promotion is slightly tangential to querying.

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?

No output schema exists, so the description rightly summarizes return fields, and it adds the non-obvious attribution contract. Only the free-text q parameter and the limit cap are left unexplained, which is minor for an otherwise complete definition.

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?

With 0% schema coverage the description must carry parameter meaning, and it largely does: category gets an eight-value example list, since gets accepted formats (30m, 6h, 7d, ISO), and confidence gets its enum values plus comma-list syntax. It leaves q and limit (default 20, max 100) entirely undocumented, which is the only real gap.

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?

Opens with a specific verb+resource ('Filter all stories ... by category, entity, since and confidence') and even clarifies scope ('including site-only briefs from official sources and wires'). That makes it distinguishable from get_story/latest_news by the multi-filter retrieval shape, though no sibling is named explicitly.

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?

Usage is implied by the filter semantics — an agent can infer this is the tool for narrowing by category/entity/time/confidence — but there is no explicit 'use this instead of search_news or latest_news when...' guidance or statement of exclusions.

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