read_observation

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

With no annotations, the description carries the full load. It does disclose the key behavioral trait relevant here — read-only, no link opening, no side effects — which is genuinely useful. It is silent on permissions, error behavior when the observation_id is missing, and any rate limits, so it is adequate but not rich.

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?

Two short sentences, front-loaded with what is read and the returned payload, followed by the boundary clause. Zero filler, 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 one-parameter read tool this is nearly complete: the return content (OCR/accessibility text plus source URL) is described even without an output schema, and the no-side-effects behavior is stated. The remaining gap is that the agent gets no guidance on sourcing a valid observation_id.

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 coverage is 0% and the single parameter has no description in the schema. The description partially compensates by framing the id as belonging to a 'cited observation,' hinting at its origin, but gives no format, source, or lookup guidance. Marginal added value over the bare 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+resource ('Read a cited observation') and even names the payload ('original Accessibility/OCR text and source URL'), so the agent knows exactly what comes back. It does not visibly differentiate itself from sibling read tools like read_review or read_topic, but the resource scope is unambiguous.

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?

'A cited observation's' implies the usage context: follow a citation/observation_id to its source. The closing clause 'Does not open links or take actions' sets a useful boundary against browsers/action tools. However, there is no explicit when-to-use-vs-alternative routing against the many sibling read_* tools.

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