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

Adds substantial context beyond the annotations: it discloses that the operation spans every page and includes openings hidden by view filters (non-obvious blast radius), that the API returns no affected count so the agent must not fabricate one, and that user confirmation is expected. These are exactly the behavioral facts annotations (readOnlyHint/destructiveHint/idempotentHint) do not convey.

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?

Four short sentences, front-loaded with the verb and scope rules, then the blast-radius caveat, the confirmation requirement, and the return-value warning. Every sentence carries distinct information with no padding.

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?

Even though an output schema exists, the description usefully warns that no affected count is returned, preventing hallucination of results. Combined with the scope and confirmation guidance, an agent has everything needed to call this destructive-adjacent bulk mutation correctly.

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 50% and the uncovered parameter is follow_id, whose semantics the description explains well (omitting it means every followed company). The schema note 'Follow ID from following.list, not company.id' is reinforced, but the description does not explain the required 'confirmed' const flag, leaving that contract implicit.

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 (mark all unread openings as read) and resource, and explicitly names the two scopes: one follow vs. every followed company when follow_id is omitted. This differentiates it from the singular sibling following.openings.mark_read without the agent needing to open either 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?

Gives a clear usage condition — confirm scope with the user first — and contrasts the two call modes via follow_id presence/omission. It stops short of naming the sibling mark_read as the narrow alternative, so routing between the two is partly inferred.

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