read_record

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses the reference-link/URL encoding mechanism, the auto-encoding of the dashed UUID to the e1cib hex token, the exact return shape, and the cold-client failure mode (field_count 0 with element_count > 0, and that re-opening the same record does not help). These are non-obvious behavioral traits an agent could not infer from structured fields.

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 first sentence front-loads the purpose well, but the body is dense and overstuffed with bilingual examples, encoding history, and a live-verified sample that go beyond what an agent needs to call the tool. It earns more of its length than a typical spec, yet still reads as heavier than necessary.

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?

An output schema exists, yet the description still supplies the failure-mode and pre-warming guidance that the schema cannot express, and the complexity of native COM automation warrants it. For this tool's complexity, nothing an agent needs to invoke it correctly — encoding, required inputs, and cold-client caveat — is missing.

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 0%, so the description must compensate, and it does for the semantically important parameters: record_type (metadata full name, e.g. Справочник.Товары), ref (natural dashed UUID form auto-encoded, or raw 32-hex token), and gherkin (adds a Gherkin state block). The remaining four parameters (host, port, capture_dir, manager_templates) are undocumented, but they are infrastructure defaults rather than the values an agent must reason about.

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 precise verb+resource: read the object-attribute VALUES of an existing populated catalog/document record, and explicitly frames it as 'natively (no per-form capture)'. This differentiates it from form-based readers in the sibling set such as read_form_descriptor and the form-value reads. An agent knows exactly what data this returns without opening another schema.

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 explains the operating condition for success (warm the client with a different record before reading a large cold record) but never names a sibling tool or an explicit 'use X instead when Y' rule. The 'no per-form capture' phrase implies an alternative but leaves the selection to inference. Adequate, but not the explicit when/when-not routing a 5 requires.

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