agy_read

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

With no annotations, the description carries the full behavioral burden. It does disclose useful operational detail (since is a 0-based offset, the default return is canonical event dicts, job_id accepts a unique prefix), but it says nothing about whether reads are non-destructive, whether the call blocks waiting for new events, or whether a cursor/offset is persisted across calls.

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?

Three compact clauses, purpose front-loaded, then per-parameter clarifications in the order the agent will encounter them. No filler sentences.

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 exists, so return values needn't be documented. However, for a polling-style log-read tool with no annotations and many confusable siblings, the description should have covered whether the read blocks, whether it is safe/repeatable, and how it relates to agy_result/agy_status. Those gaps leave the agent under-informed.

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 0% (titles only), so the description must carry the load, and it documents all three parameters: the meaning and base of `since`, the accepted `translate` values with the default behavior spelled out, and the prefix-matching rule for `job_id`. It stops short of explaining how the raw/claude/codex wire formats differ, keeping it from a 5.

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 first sentence gives a specific verb and resource: 'Read events from a job's event log.' That is unambiguous about what the tool does. What it lacks is any differentiation from siblings such as agy_result or agy_status, which an agent must distinguish to pick the right tool.

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?

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. Nothing tells the agent whether to call agy_read versus agy_result (for results) or agy_status (for state), so selection rests entirely on inferring from the name.

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