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

Annotations already cover safety (readOnlyHint, destructiveHint=false), so the description's value-add is the disclosure of the 2026-forward-only corpus and the 'up to 10 terms' ceiling — both non-obvious constraints that affect whether a call will succeed. It also notes the return shape (summaries plus pagination), though it does not say what happens with zero matches or how ranking works.

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 short sentences, front-loaded with the defining constraint and followed by routing guidance, then limits, then return shape. Nearly every clause earns its place; only the endpoint path is arguably redundant for an agent that never constructs URLs.

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 usefully states that results are bill summaries with pagination. Combined with the corpus-scope warning and the alternative-tool routing, an agent has enough to decide and call correctly; only edge-case behavior (empty result sets, term matching rules such as stemming/phrase handling) is unstated.

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 limit, offset, state, and keywords are all documented in the schema already. The description reinforces the keywords cap ('Up to 10 terms') and gives an example of valid term formatting, but adds nothing about state filtering or pagination semantics. Baseline 3 is appropriate when the schema carries the load.

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 mechanism (AND-semantics keyword search where every term must appear) plus the endpoint, which is far more precise than the sibling 'search_bills' and immediately distinguishable from 'semantic_search_bills'. The title and first clause agree and leave no ambiguity about the resource.

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?

Explicitly names the selection condition (user gives specific words that all must be present) with a concrete example, and routes to both alternatives: semantic_search_bills for natural-language questions and search_bills for structured filters. This is exactly the when/when-not/alternative structure the dimension rewards.

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