session_events

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

With no annotations available, the description carries the full burden and does real work: it discloses ordering (oldest first), the exactly-once delivery guarantee across calls, the cursor-advancing effect of a normal read versus peek, and a prompt-injection warning about untrusted payloads. It does not say whether the call blocks or returns empty when no events exist, which is the one behavioral trait an agent still has to guess.

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 sentences, zero waste, and the core behavior (what is read, in what order, with what delivery guarantee) is front-loaded before the safety warning and the peek hint. Every sentence adds distinct information.

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?

There is no output schema, and the description never sketches the shape of an event (fields, sender, type), so an agent knows the delivery contract but not the payload structure. For a read tool with fully documented parameters and strong behavioral notes, that is a minor but real gap.

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 100%, so the baseline is 3, but the description goes beyond restating fields by explaining the consumption consequence of peek ('look without consuming') and framing the read as cursor-advancing by default. The session_id and project_path constraints are left entirely to the schema.

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 the events addressed to this session') with scope qualifiers (direct and broadcast, oldest first, delivered exactly once). It never names a sibling such as session_wait, so an agent must infer the difference between reading buffered events and waiting for new ones.

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 only usage instruction is 'Use peek: true to look without consuming,' which is guidance about a parameter rather than about when to choose this tool over alternatives. There is no statement about when not to call it or how it relates to session_wait, so usage is only implied by the description of what it returns.

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