append_run_receipts

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the write-type nature isn't fully disclosed by annotations. The description discloses a safety contract (no prompts, no raw arguments, no credentials) which adds behavioral context. However, it doesn't clarify the role of expected_revision (optimistic concurrency), what happens on revision mismatch, or whether appends are idempotent.

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?

Single, compact sentence with a clear verb-object structure and useful scope qualifiers. No wasted words, well front-loaded. Slightly verbose with the triple exclusion list but each item adds safety-relevant meaning.

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?

Despite having an output schema, the tool is a mutation (readOnlyHint=false) with a concurrency mechanism (expected_revision) that is never explained. It's part of a large run lifecycle toolset with 27 siblings, yet the description gives no placement in that workflow. The safety constraints are useful but the semantic burden of 3-parameter operation with 0% schema coverage is not met.

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, but the only parameter mentioned implicitly is 'receipts' (the content being appended). run_id and expected_revision are undocumented both in schema and description. The description adds no explanation of what the receipts array must contain structurally or what expected_revision governs.

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 states a specific verb ('append') and resource ('safe live stage/tool receipts'). The scope qualifiers ('without prompts, raw arguments, or credentials') add precision about what content is acceptable. However, it doesn't explicitly contrast with sibling tools like get_run_events or poll_run_events which could also involve receipts/events, so it's clear but not strongly differentiated.

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 implies usage by describing what it appends, but provides no guidance on when to use this vs alternatives. It doesn't mention concurrency, the purpose of expected_revision, or when this would be appropriate relative to commit_host_stage or finalize_host_run siblings. Context is thin given the 27 sibling tools.

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