history_session_read

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, consistent with 'Read'. Beyond that, the description adds genuine behavioral detail: responses are paginated UTF-8-safe pages, max_bytes defaults to 32 KiB and is capped at 64 KiB, and completing the source requires following next_cursor. It stops short of documenting error behavior or what happens with an invalid expected_hash.

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?

Two sentences, no filler, with the purpose front-loaded and pagination behavior second. Dense but every clause carries information; minor jargon ('lossless numeric Markdown archive', 'UTF-8-safe pages') costs it the top mark.

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?

With no output schema, the description usefully sketches the return shape (paged responses plus a next_cursor) and the read-only safety profile is covered by annotations. However, for an 8-parameter tool with 0% schema coverage, half the inputs—including the integrity-check parameter expected_hash and the three root/dir parameters—are left for the agent to guess.

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% across 8 parameters, so the description carries the full burden and only partially delivers. It explains max_bytes (default and 64 KiB cap) and constrains the addressing mode (number vs. path), but leaves cursor (called 'next_cursor' in prose, a naming mismatch), history_dir, project_root, workspace_root, and expected_hash entirely unexplained.

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 specific verb and resource ('Read one lossless numeric Markdown archive') and immediately distinguishes itself from the sibling history_session_search by naming it as the source of valid paths. An agent can tell this is the read-back counterpart to search without opening either 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?

Explicitly routes the agent: use a number or a path 'returned from history_session_search', and follow next_cursor to get the full source. This gives clear context for when to reach for this tool, though it names no exclusion conditions and never mentions the sibling history_session_validate.

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