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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses caching, free vs paid tiers, response fields at each tier, gated:true behavior, the exact withheld fields, and the fact that live mode returns a payment challenge instead of data. This gives an agent an accurate mental model of what will happen.

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?

Four dense, front-loaded sentences deliver a large amount of information with zero filler. The core purpose appears first, then response contents, then gating, then the paid alternative. Every sentence earns its place, and the structure supports quick decision-making.

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?

Given no annotations and no output schema, the description is remarkably complete: it enumerates free-tier response fields, names exactly what is withheld, explains the gated flag, specifies live-mode cost and challenge payload, and notes the settlement/retry path. An agent has enough to select and invoke the tool 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 coverage is 100%, so the baseline is 3. The description adds meaningful behavior beyond the schema by detailing what live:true triggers (the 402 payment challenge with accepts[] and payTo) and what the gated response names. It also clarifies address scope to 'on Base', which the schema does not state.

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 opens with a precise, actionable statement: 'Reputation score 0-100 for a specific agent address on Base'. This clearly identifies the verb (score), resource (agent address), and network scope, and it distinguishes the tool from batch or comparison siblings by emphasizing 'specific agent address'.

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?

The description clearly instructs when to use the default free cached snapshot versus passing live:true for a paid fresh re-score, including cost and response differences. It does not explicitly name alternatives like mainstreet_scores_batch, but it gives strong context for choosing between the two modes of this tool.

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