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

Annotations already declare this as a read-only, idempotent, non-destructive operation, so the safety bar is covered. The description adds meaningful domain behavior: the row grain (measure x future year) and the community-vs-technical split where a measure carries either target_statement or target_value in its own unit (explicitly not money).

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, then the row grain and value semantics, then the filter hint, with no filler sentences. Slightly dense with the regulatory citation, but every clause carries information.

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?

There is no output schema, so the description shoulders the burden of explaining the return shape, and it does so by naming the discriminators (target_statement vs target_value) and the row unit. Combined with annotations covering the safety profile, an agent has enough to call it correctly; only pagination nuance (deferred to the schema) is unaddressed.

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 all four parameters (page, year, per_page, los_measure_id) are already documented and the baseline is 3. 'Filter by measure or year' restates what the schema already says and adds no new syntax or range detail.

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 ('List proposed levels of service') and adds distinguishing granularity ('one row per LoS measure and future year'). It is clear what the tool returns, but it never names the near-neighbors (list_infrastructure_los_targets, list_system_los_targets, list_los_measures) to disambiguate within a very crowded LoS family.

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 closing clause 'Filter by measure or year' implies the supported narrowing, but there is no when-to-use framing, no when-not condition, and no routing to an alternative sibling. Usage is inferable but not stated.

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