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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety needs no restating. The description adds real value by naming the returned fields and flagging that results are paged, plus disclosing the underlying GET /companies call — only the absence of total-count/termination behavior keeps it from a 5.

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 clause plus endpoint, zero waste, with the scope and payload fields front-loaded before the paging note. Nothing in it is redundant or buried.

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 correctly compensates by listing the fields returned, and paging is covered with schema help. It is nearly sufficient for a simple two-param list tool; only pagination termination (what an empty next_page means) is left unstated.

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%: page, its default, and the next_page chaining hint are all documented in the schema itself. The description's "paged" adds only a framing cue, not semantics beyond the structured fields, 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+resource ("List client companies") with the returned fields enumerated (name, address, website, owner) and the backing endpoint noted. It does not distinguish itself from cats_search_companies or cats_get_company, so an agent must still infer when a list beats a search.

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?

"List ... paged" implies bulk enumeration rather than targeted lookup, and the schema's note about passing next_page reinforces the paging workflow. But no alternative (search_companies, get_company) is named and no condition for choosing among them is given.

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