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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no repetition. The description still adds real behavioral value: it specifies cursor-based pagination via limit and cursor and that the response carries a next cursor, and it pre-empts a common misread by stating the call does not create, generate media, or send anything. It does not discuss rate limits or permission/access-scope semantics, which keeps it below 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?

Three sentences, front-loaded with the operation and scope before pagination details and the negative-capability caveat. Slightly over-indexed on enumerating returned fields, which the output schema already covers, but nothing is truly wasteful.

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-field enumeration is a bonus rather than a necessity. Scope, pagination mechanics and the read-only caveat are all present; the only gaps are what 'accessible' means in terms of permissions and the limit defaults, both minor for a two-parameter list call.

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 0%, so the description bears the burden. It names both parameters and frames them as a pagination pair, and 'plus the next cursor' tells the agent how to continue iterating. It omits the limit default (50) and the 1–100 bounds, and never explains that cursor must be a UUID taken from a prior response.

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 plus resource and scope ('List accessible fixed-video campaigns in the connected organization'), which cleanly separates it from the singular campaigns_get and from the other *_list siblings. An agent knows immediately this is the collection-listing endpoint for campaigns.

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 only implied: retrieving campaigns via pagination. The description does not say when to prefer this over campaigns_get, campaigns_validate, or campaign_production_get, nor any prerequisite (e.g., needing an organization context). The closing 'This read does not create campaigns, generate media or send messages' rules out write paths but is not genuine when-to-use guidance.

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