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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add the semantics that matter: it returns the most recent price at or before the timestamp, not an exact-match lookup — a genuinely important behavioral trait for the caller. It omits what happens when no prior price exists (error vs null) and says nothing about rate limits, but for a read-only lookup this is solid added context.

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?

Three sentences, front-loaded with the core behavior before the use cases. The final sentence's three examples are slightly padded but each is concrete and short; nothing is wasted outright.

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?

There is no output schema, so the description should carry return shape — 'Returns the last known price' hints at a scalar but doesn't say whether the response includes the actual matched timestamp or asset metadata. The no-data case (timestamp earlier than any known price) is also unaddressed, leaving real gaps for a 4-parameter tool.

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%, including the symbol/asset_id mutual exclusivity and the timestamp semantics, so the schema already carries the load and baseline 3 applies. The description adds no parameter-level detail (e.g. asset_class resolution, timezone/precision caveats) beyond restating the timestamp behavior.

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 ('Get price') plus the crucial resolution semantics ('last known price at or before the given timestamp'). It implicitly distinguishes itself from range/history siblings ('a point in time'), but never names get_price_history or get_price_range, so differentiation is left to inference.

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?

'Use this to value a position, settle a trade, or anchor a calculation to a specific moment in time' gives concrete usage contexts that map to the point-in-time semantics. It stops short of exclusions — no guidance on when to prefer get_price_history or get_price_range instead.

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