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

Goes well beyond the annotations: it says conversations are re-pointed, that a channel collision archives one side without deleting any message, that tags/notes/events are combined, that the master is completed without overwriting, that the satellite leaves the lists, that no message is sent, that 'write' scope is required, and that merge chains are rejected. The annotations only flag destructive/idempotent; the description supplies the actual blast radius.

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-loads the action and scope in the first clause and packs genuinely load-bearing details (archival behavior, reversibility, prohibitions). It is dense and slightly run-on with parentheticals, but virtually no sentence is 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?

For a destructive, irreversible-looking operation with no output schema, the description covers effects, precedence rules, reversibility handle (merge_id), confirmation requirement, and authorization scope. An agent has everything needed to decide and invoke safely.

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 already 100%, so baseline is 3, but the description adds real meaning: it clarifies the asymmetric direction (satellite is absorbed, master survives) and explains the purpose of confirm as the explicit same-person attestation. It also documents the returned merge_id, which feeds the undo call.

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 (merge satellite_lead_id INTO master_lead_id) and immediately disambiguates the direction, which is the one thing an agent could get wrong. It also names the sibling tool that reverses it (ficiel_unmerge_leads), so it is clearly distinguishable from the surrounding ~70 tools.

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 (two fiches of the same person) and a prohibition (fusion chains are forbidden), plus the guard that confirm must be true. It routes to the undo path (ficiel_unmerge_leads) with its precondition ('tant que rien n'est purgé'), but does not compare against non-merge alternatives such as update_lead.

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