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

With no annotations provided, the description carries the full burden. It discloses that the tool is public (no auth), that it returns nulls for absent blocks, and that older itineraries have none of them. This is valuable behavioral context for an agent. The description could be slightly richer (e.g., clarifying if nin is idempotent or if there are rate limits), but for a read-only tool with no annotations, this is well above average.

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 description is three sentences long with no filler. The first sentence front-loads the purpose and contents, the second adds auth context, and the third explains the return behavior. Every sentence earns its place.

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 tool with no output schema and only one simple parameter, the description covers the key aspects: what it reads, what it returns (with nulls for missing blocks and note on older itineraries), and auth requirements. It doesn't explain pagination, size limits, or error conditions, but for a single-object read with an implied one-to-one mapping, this is sufficient.

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?

There is only one parameter (itinerary_id) and schema description coverage is 0%, so the description must compensate. The description states that the tool reads an itinerary's dossier and implies that the input is the itinerary identifier. While it doesn't elaborate on the UUID format (the schema does that), it adds essential context about what the parameter identifies and what the output relates to, which is sufficient for an agent to infer the parameter's meaning.

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 explicitly states the verb 'Read' and specifies the resource 'itinerary's planning dossier', then itemizes the contents (legs, seasonality, cost model, booking order, field notes, open choices). This clearly distinguishes it from sibling tools like 'get_itinerary' (which likely returns a simpler overview) and 'set_itinerary_dossier' (which writes).

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?

The description says 'Public — no token needed', which is a clear usage precondition. It also notes that older itineraries return nulls for blocks, implying this tool is appropriate for retrieving detailed planning data. However, it does not explicitly state when to choose this over alternatives like 'get_itinerary' or 'get_pricing', nor does it mention any exclusions for using it on itineraries that lack the dossier.

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