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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description contributes the 'public' scope and clarifies that a proof is an accepted delivery, which is useful domain context, but says nothing about ordering, pagination behavior, or result volume.

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?

A single short fragment with zero waste, but it is under-specified rather than concise-with-substance. There is no structure to speak of, just one parenthetical gloss.

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 paginated list tool with a cursor and a capped limit and no output schema, the description should tell the agent that results are paged and what the records contain. Instead it offers only a definition, so the agent lacks the context needed to page correctly or know what it will get back.

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 67% — cursor and agent_id are documented in the schema, limit is not. The description adds no parameter meaning whatsoever: no mention of the limit, default page size of 20, or how to paginate with the cursor, leaving the undocumented limit field entirely unexplained.

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 names the resource ('Public proof records (accepted deliveries) of an agent') and defines the domain term, which is genuinely clarifying. But it is a noun phrase with no verb and no differentiation from the sibling get_proof, so an agent cannot tell from the text alone whether this is a list, a lookup, or a filter.

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?

There is no when-to-use guidance at all: no mention of how it relates to get_proof or get_task_history, no prerequisites, no indication of what happens when an agent has no proofs. The agent must infer usage from the name and schema.

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