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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description contributes the referential-integrity rule (blocked while referenced by a class, fee, or trial session), which is genuinely new behavioral information; it stops short of saying whether the removal is reversible or what the refusal returns.

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?

Two short sentences, no filler, with the core action first and the blocking condition second. Nothing is wasted and nothing important is 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?

For a one-parameter destructive tool with annotations covering the safety profile and no output schema, the description supplies the key failure mode an agent needs. Minor gaps remain around reversibility and the shape of the refusal error, but an agent can call this 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 100% with a single required `id` parameter already documented as "The subject's id." The description adds nothing about format, source of the id, or whether it accepts names, so the schema does all the work.

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 ("Remove one subject") and the singular "one" implicitly contrasts with bulk siblings like merge_subjects. It is clear, but it never names list_subjects (to find the id) or merge_subjects (the alternative when subjects must be combined).

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?

"Refused while a class, fee or trial session still uses it" gives a concrete precondition that tells the agent when this call will fail, which is real usage guidance. It does not, however, point to an alternative path (e.g., reassigning or merging) when that precondition blocks the call.

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