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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real behavior: ranged filters exclude tokens with no value rather than treating them as zero, health is a 0-100 score set when the scorecard is written, and verdict encodes value accrual classes. It does not discuss ranking/pagination behavior, so it is strong rather than exhaustive.

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-loads the purpose and the return shape, then organizes the rest into 'Filters:' and 'Fields:' blocks so the dense content is navigable. The field glossary is long, but because there is no output schema each entry adds meaning that the bare enum in the schema does not.

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 13-parameter, no-required-argument screening tool with nested min/max objects and no output schema, the description covers filter usage, field meanings, and the null-handling rule. The main residual gap is ranking and result-window behavior, which the limit/order/sort parameters imply but the text does not state.

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?

With schema description coverage at only 23% and 13 parameters, the description carries the load by explaining the min/max range object with a worked example, the value sets for lens and verdict, comma-separated flow_model, and how each field is measured. It omits explicit semantics for sort, order, and limit, which remain inferable only from the 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 and resource ('Screen the whole Book') plus the return shape ('compact ranked rows'), and the parenthetical '(all scored tokens)' scopes it against the listing/search siblings. An agent can tell this is the full-book screener rather than a single-token lookup or a text search.

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?

Gives concrete filter mechanics — enumerated lens/verdict values, comma-separated flow_model, stale, query substring, and a min/max range example — so the agent knows how to drive the screen. It never states when to prefer this over tc_list_tokens or tc_search_tokens, so it stops short of explicit alternative routing.

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