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

Annotations only give readOnly/idempotent/destructive hints; the description adds operational constraints the annotations cannot: 1-100 codes per call, 255-char limit, 20,000-code list cap, and the fact that it does not count against the 30 requests/hour limit. It also discloses the underlying endpoint.

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?

Front-loaded with the WRITE marker, then limits, then id provenance, then exclusions and rate-limit note. Dense but every clause carries actionable information; no filler.

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 does not say what the call returns (e.g., accepted vs. rejected codes), which is the one thing an agent might still want for a bulk write. Everything else — limits, provenance, exclusions, rate-limit exemption — is covered.

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% and the schema already carries per-parameter descriptions, so baseline is 3. The description adds provenance for access_list_id and a list-level capacity constraint (20,000) that appears nowhere in the schema, which is genuine added meaning.

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 and resource ('add access codes ... to a link's access-code list') plus the outcome ('so those people can start the exam'). No sibling tool touches access-code lists, and the description's scope (add-only) makes that distinction unambiguous.

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?

Explicitly says when to use it (to let people start an exam), where the required id comes from ('classmarker_list_groups_links_exams (links[].access_list_id)'), and what it cannot do ('Only adds; removing codes is not offered'), which functions as the when-not clause.

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