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

Annotations already declare readOnly and idempotent, but the description adds substantive behavior: whole-filing association rather than allocated amounts, overlapping issue buckets, all versions acquired before latest-period selection and local issue filtering, and a real latency warning ('can take hours'). The cursor instruction ('follow collecting cursors before interpreting final typed rows or SQL datasets') discloses a non-obvious execution contract that would otherwise cause misreads.

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?

Purpose and the key caveat are front-loaded in the first two sentences, then performance, cursor, and handoff notes follow in priority order. It is dense but every sentence carries operational information; only the repeated references to versions/cursors verge on redundancy.

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 aggregation tool with an output schema and full annotation coverage, the description supplies the remaining load-bearing context: association semantics, overlap caveat, latency, cursor discipline, and cross-tool handoffs. An agent has enough to call it correctly and to interpret the results without over-reading them as allocated issue spending.

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, but the description adds meaning the schema does not: years is an explicit analytical scope, issue_code must come from uslobbying_list_reference topic issue_codes on the first call, and client_id should be resolved from uslobbying_get_client_profile candidates. The cursor guidance further frames how row_sets and continuation interact with acquisition and totals.

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 first sentence names a specific verb (aggregate) and resource (income/expense amounts on quarterly filings keyed to issue_code across explicit years). It immediately disambiguates the semantics with 'whole-filing association, not allocated issue spending; issue buckets overlap', which no sibling would claim. The handoff sentence to uslobbying_search_filings clarifies the boundary against that sibling.

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?

It gives concrete operating advice: 'Broad scans can take hours; narrow client_id or registrant_id when appropriate', and tells the agent to pass a selected filing UUID to uslobbying_search_filings for the complete record. That covers when to narrow and where to escalate, but there is no explicit when-not-to-use versus siblings like uslobbying_get_contributions or uslobbying_dataframe_query.

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