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

Annotations declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is already covered. The description adds valuable context beyond annotations: it clarifies that nothing said in the current conversation is stored and that a new budget only persists as a resting commitment (referencing create_standing_bid). It also explains the intended use of notes ('shape what you say, never read them back verbatim'). This is rich for a read tool, though it could mention response format or caching.

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 front-loaded with the primary purpose and timing. It is a bit long (four sentences) and includes some verbose phrasing like 'e.g. re-asking a budget right before you help them make an offer on the XP marketplace,' but every sentence still earns its place by conveying a distinct usage rule or behavioral caveat.

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 read-only retrieval tool with one required parameter, full schema coverage, annotations covering safety, and an output schema (so return values need not be described), the description is complete. It covers timing, purpose, behavioral caveats, and cross-references the sibling tool create_standing_bid. Nothing critical is missing for correct invocation.

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% – the schema already fully documents event_ids ('Event IDs the user has settled on. Usually one.'). The description does not add any parameter syntax, format, or edge-case details beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Clearly states what is retrieved (budget per ticket, quantity, date flexibility, notes) and its temporal position ('once the user has settled on an event, before quoting prices'). The phrase 'what they already told XP' is slightly colloquial but still defines the resource as stored user-provided context. It doesn't explicitly distinguish itself from get_user_account, but the scope is specific enough to be useful.

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?

Explicitly says when to use it ('once the user has settled on an event, before quoting prices') and why ('stops you asking twice'). It also gives a constraint ('use saved notes to shape what you say, never read them back verbatim'). However, it does not name alternative sibling tools for retrieving user data (e.g., get_user_account) or say 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.