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

The description adds substantial behavioral detail beyond the readOnlyHint/destructiveHint annotations: it documents the exact calculation chain from net_revenue through net_profit, and warns that per-product rows do NOT sum to account tiles because refunds, account fees, and unattributed ad spend are account-level. This is precisely the kind of non-obvious behavior an agent needs to interpret results correctly.

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?

The description is dense but efficient: three sentences pack the output contents, formula chain, and a critical non-additivity caveat. It is front-loaded with the summary purpose and formula detail earns its place. A small amount of structure could improve scannability, but nothing is wasted.

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?

The description thoroughly explains what the summary contains and how metrics relate, which is valuable given there is no output schema. However, it omits semantics for top_n, currency, and group_by, all of which are needed to call the tool with intent. The output behavior is well covered, but the input space is only partially explained.

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 description coverage is only 50%, with top_n, currency, and group_by lacking schema descriptions. The tool description does not compensate: it never explains that top_n controls the number of top product rows, what currency affects, or how group_by=child vs parent changes aggregation. The only indirect hint is 'top product rows,' which is insufficient for undocumented parameters.

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 specific resource and action: 'Profit & Loss summary for a date window' and enumerates the exact contents: account tiles for sales, fees, COGS, ad spend, gross profit, contribution margin, net profit, TACoS, plus top product rows. This clearly distinguishes pnl_summary from lower-level siblings like pnl_by_asin, pnl_expenses, and pnl_refunds by establishing it as the account-level summary tool.

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 implies the tool is for a high-level account P&L view over a date window, but it never explicitly states when to prefer this tool over pnl_breakdown, pnl_period_cards, or pnl_mcf_summary. There is no exclusion guidance such as 'use pnl_by_asin for per-ASIN detail' or 'use pnl_expenses for expense lines.'

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