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

Annotations mark it destructive and idempotent, but the description goes well beyond them: it enumerates exactly what is restored (conversations, messages, tags, notes, events) and what is reverted (master fields), explains the tags_policy fork for tags added after the merge, discloses refusal reasons, and states no message is sent and write scope is required.

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 core action and the id's provenance, then the side effects, then the policy, then failure modes. Dense but every clause carries information; the run-on middle sentence could be broken up, keeping it just short of a 5.

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 destructive, no-output-schema mutation, the description covers restoration semantics, policy branching, refusal behavior, message side effects, and required scope — everything an agent needs before invoking it.

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%, so baseline is 3, but the schema's tags_policy description is just 'keep_master ou copy_both' while the tool description actually explains what the parameter governs (tags added after the merge) and the effect of each value. lead_id and merge_id are also disambiguated as master fiche vs. fusion to undo.

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?

Names a specific verb (unmerge/défaire une fusion) and resource (two leads), and ties the merge_id input directly to its source tool, ficiel_list_lead_merges. An agent can distinguish it from ficiel_merge_leads without opening 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?

Points the agent at ficiel_list_lead_merges as the source of merge_id and states the refusal conditions (purged fiche, reattached elsewhere, active conversation holding the channel), which effectively defines when the call will fail. It never explicitly contrasts itself with ficiel_merge_leads or says when not to use it, so it falls short of a 5.

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