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

Annotations already establish this as a safe read (readOnlyHint=true, openWorldHint=false). The description adds real behavioral context beyond them: results come back in segment order and include a header. It does not disclose pagination semantics (limit capped at 60, next_start continuation), which matters for a segment-windowed reader.

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?

A single front-loaded sentence opening with the verb, with no filler. It is efficient, though terseness here shades into under-specification rather than optimal density.

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 output schema covers return values and annotations cover safety, so the description is not obligated there. But for a four-parameter reader it omits the recall→read workflow, pagination via start/limit/next_start, and how segment_id windowing interacts with ordered reading, leaving real gaps.

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 75%, close to the high-coverage baseline, and the description adds no parameter meaning at all. `limit` has no description in the schema and is not compensated for here, so the one heavily-used knob (page size) remains opaque.

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?

Names a concrete verb ("Прочитать") plus the resource ("документ") and concretizes it with examples (письмо, дневниковая запись, глава), and states the read mode: ordered segments with a header. However it never mentions the sibling `recall` or explains how this differs from it, so an agent must infer the relationship from the schema instead.

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 gives no when-to-use or when-not-to-use guidance and never references the alternative `recall`. The workflow hint (doc_id/segment_ids come from recall) appears only inside the parameter descriptions, not in the description itself.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds that retrieval is hybrid (meaning + words), which tells the agent query formulation matters. It does not mention the top cap of 10 or any ranking behavior, so the added context is modest.

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?

A single front-loaded sentence naming the action, scope and method, with no filler. It is efficient, though it is sparse enough that the brevity shades into under-specification rather than pure conciseness.

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, so return values need not be explained, and the annotations cover the read-only nature. What is missing is routing guidance relative to read_document and any hint about result size limits, leaving the definition only minimally complete for a tool that competes with a sibling.

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 67% – query and only_mine already carry descriptions, while top does not. The description only echoes the topical-query notion ('по теме', 'смысл + слова'), adding no detail about the top cap or only_mine scope beyond what the schema says. 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 gives a specific verb and resource ('Найти фрагменты корпуса Толстого по теме') and even names the retrieval method (hybrid semantic + lexical search), so the agent knows exactly what the tool returns. However, it never distinguishes this from the sibling read_document, so the boundary between the two remains unclear.

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?

Beyond the implied 'use this to search by topic', there is no explicit when-to-use, when-not-to-use, or comparison to the sibling read_document. An agent facing both tools has no stated rule for choosing between them.

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