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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context beyond them: X-API-Key requirement, org scoping, the non-error empty-list behavior for unknown keys (total 0), and the full response envelope with paging semantics. This is exactly the operational detail an agent cannot infer from the annotations.

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?

Front-loaded purpose sentence, then labeled when-to-use / when-not-to-use clauses, then edge-case and return-shape notes. Dense but every clause carries actionable information; nothing is padding.

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?

With no output schema, the description compensates by naming the return fields {decisions, total, next_cursor, has_next} and the empty-result edge case. For a 3-parameter, read-only list tool, an agent has everything needed to call it and paginate correctly.

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%, so the baseline is 3, but the description goes further by explaining the cursor chaining contract ('Pass next_cursor as cursor for the next older page') and warning that agent_name is not accepted, which shapes how the required agent_public_key must be sourced. It does not restate schema constraints, so it adds rather than repeats.

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?

Specific verb+resource ('List recent decision events for one agent') with explicit scope (by public key, in the API key's org, newest first). It is immediately distinguishable from siblings like get_proof, log_decision and log_outcome, which it also names.

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?

Provides explicit 'When to use' (review logged history, pick an event_hash for get_proof, page history before linking an outcome) and 'When NOT to use' clauses that route to get_proof and log_decision/log_outcome. The Managed Mode caller constraint (resolve public_key from a prior log_decision or register_agent) is a concrete usage condition rather than vague advice.

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