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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context: it explains that size is 'the sum of BDC pieces with its basis, pricing modal and ranged across pieces, maturity with basis', and that the lender group includes 'every BDC that holds or held a piece, each row the lender's own figures, plus lenders named on a deal'. This goes beyond the annotations by clarifying the aggregation and scope semantics, though it does not describe return format or pagination.

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 a single dense sentence that packs in a lot of information, but it is somewhat run-on and could be better structured. It front-loads the core definition ('one borrower group in one instrument class') and then lists components, but the long parenthetical chain makes it harder to parse than necessary. It earns its place but could be split into clearer sentences.

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 single-parameter read-only tool with 100% schema coverage and no output schema, the description is fairly complete. It explains what the facility is, how size is computed, what the lender group includes, and that history is covered. The main gap is that it doesn't explicitly describe the return shape, but with no output schema and a read-only annotation, the description carries enough context for an agent to invoke it correctly.

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 100%, so the schema already documents the dfx_id parameter. The description adds context by specifying the id format ('dfx:pc:<uuid>') and valid sources (get_borrower_capital_structure, search_credit_maturities, or an event), which is useful. However, the description itself does not explain the parameter beyond what the schema already provides, so baseline 3 is appropriate.

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 states a specific verb ('get') and resource ('one facility') and enumerates the content: size, pricing, maturity, lender group, and history. It distinguishes itself from siblings like get_borrower_facilities and get_borrower_capital_structure by focusing on a single facility with lender group and history, though it does not explicitly name those siblings.

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 usage: call this when you need a single facility's full detail including lender group and history. It does not explicitly state when to use it versus alternatives like get_borrower_facilities or search_credit_maturities, but the input schema's dfx_id description references get_borrower_capital_structure, search_credit_maturities, or an event, providing some routing context.

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