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

Despite annotations covering read-only/idempotent safety, the description adds substantial behavioral context beyond them: fact classes (filed/derived/carried/inferred) with their meanings, the mark vs impairment distinction, the presence of non-accrual events, explicit exclusions (defaults, restructurings, covenants not on tape), entitlement gating (first 5 rows, locked.count/by_type), and what is never returned (contact values, decision-maker names). This is genuinely useful for correct invocation.

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 and front-loads the resource concept, but it is long and mixes usage, semantics, caveats, and access policy in one block. Some sentences earn their place (fact classes, non-accrual, entitlement), while the marketing CTA at the end is extraneous. It could be more skimmable.

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 search tool with no output schema, the description covers the key behavioral traits, data semantics, and access limitations. It does not explain return format or pagination beyond cursor mention in schema, but entitlement/locked fields are described. Complete enough for an agent to call correctly, though output shape remains implicit.

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 62%, leaving several parameters (query, sort, min_lenders, maturity_before, bdc_advisers_only, held_only, limit) without schema descriptions. The description compensates by explaining query behavior (trigram across names/aliases, distinct rows), what no-query filters do, and the meaning of several filters. Enum-based params like sort and class remain unexplained in text, but overall the description adds meaningful semantic grounding.

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 clearly states the resource — the private credit capital structure graph built from BDC schedules of investments — and the tool title names the entity types (lenders, BDCs, borrowers, sponsors, credit funds). It does not explicitly route the agent away from similarly-named siblings like search_private_credit_changes or get_credit_provider, but the scope is specific enough to be useful.

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?

Usage is implied through the description of behaviors: with a query it name-matches, without a query it lists providers or borrowers via filters. However, it does not state when to use this tool versus siblings such as search_entities, resolve_name, get_credit_provider, or search_credit_stress. The agent must infer routing from the semantics.

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