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

Annotations already establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the bar is safety-covered. The description adds substantive behavior beyond that: edited or truncated files are refused, evidence is merged by a stated rule, and resume eligibility depends on missing evidence plus a failed or budget-deferred attempt — exactly the operational detail an agent needs.

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 purpose is front-loaded and every clause carries information, but the whole description is one long sentence with nested parentheticals that makes it dense to parse. It is efficient but could be split for readability.

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 explicit return-value explanation is not required, and the description nonetheless covers seal checking, hypothesis state, and resume semantics well. The only gap is that it does not tie the 'sequences' parameter to the pinned-input check, though the schema documents that parameter fully.

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 baseline is 3. The description reinforces that 'run' is a research run file, but it does not add meaning for 'sequences' (the current corpus to check against pinned inputs) or 'run' beyond what the schema already documents.

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 opens with a specific verb and resource — 'Read a research run file without running anything' — and then enumerates exactly what is reported: seal validity, hypothesis verdicts and evidence-merge rules, resume-eligible hypotheses, and what resuming would do. This clearly separates it from resume_research_run and run_discovery_programme, which actually execute work.

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?

'without running anything' and 'what resuming would do' imply the inspection-before-resume use case, giving an agent clear context for choosing this over resume_research_run. It stops short of explicitly naming alternatives or exclusion conditions, so it is strong but not fully prescriptive.

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