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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, and the description goes well beyond them: a GLOBAL shared quota of 50 analyses/hour across all MCP clients, explicitly no per-client limit, and the 429 error semantics with an explicit anti-retry instruction. This is exactly the kind of rate-limit and failure-mode context an agent needs before calling.

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?

Purpose and outputs are front-loaded before the quota/retry caveat, and every sentence carries information. It is a dense single flow, but nothing is redundant or 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 one-parameter, read-only, no-output-schema tool, the description covers input scope, processing pipeline, what is extracted, the parcel-identification step, and the rate-limit/failure behavior. Nothing an agent needs in order to call it correctly is missing.

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?

Only one parameter with 100% schema coverage, so the baseline is 3. The description adds value by qualifying the URL as a French real-estate listing and enumerating supported sources (SeLoger, PAP, Bien'ici, Le Figaro Immobilier), which tells the agent which URLs are in scope beyond the bare 'URL complète de l'annonce immobilière' in the schema.

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 (analyse/extrait/identifie) and resource (URL d'une annonce immobilière), plus the concrete outputs (surface, DPE, commune, terrain, prix) and the cross-referencing with the DPE database. This clearly separates it from siblings like find_parcelles_by_address or get_dpe, which start from an address or a parcel rather than a listing URL.

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?

Usage is implied: you call it when you have a French listing URL. The retry guidance ('NE PAS réessayer immédiatement' on 429) is genuinely useful operational guidance, but the description never states when to prefer this over the sibling parcelles tools, nor any exclusions or prerequisites beyond the input URL.

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