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

Beyond destructiveHint=true, it discloses that the 404 is immediate across all sites, that the deletion is irreversible, and that a re-created link is a distinct new entity rather than a restored one. It also notes the audit trail ('a line in its history') and the write-permission requirement, which annotations cannot express.

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?

The effect is front-loaded, but the internal ticket reference '(PM-1168)' and the colloquial clause 'the clouds and cards there say the thing is not available' restate the preceding 404 sentence rather than adding information. Three sentences of prose where two tighter ones would do.

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 single-parameter destructive tool with no output schema, the description covers effect, scope, irreversibility, permission and audit trail. It does not mention behavior on an already-deleted or unknown embedId, which is the one remaining gap.

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% and the schema already tells the agent the embedId comes from list_registry_embeds. The description adds nothing about the parameter itself, 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?

The description uses a concrete verb ('take ... link down') on a specific resource enumerated as a term's, claim's or set's embed, and the 404 propagation makes the effect unambiguous. It separates itself from delete_wiki_embed by scoping to registry embeds, though it never names that sibling as the alternative.

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?

It gives a clear use context — you want the link to return 404 everywhere it appears — plus an explicit eligibility condition ('Only for somebody who may write in the project'). It stops short of naming when-not or which sibling to use for a non-registry embed.

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