agent_session_log

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

With zero annotations, the description carries the full burden — and it delivers. It discloses the "warn" alias mapping, the fallback-to-"info" coercion for invalid levels, and even explains the design rationale ("a logged entry at the wrong level beats no entry at all"). This is exactly the kind of failure behavior an agent needs to predict results.

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 content is front-loaded and the first sentences are tight, but the description is longer than it needs to be: it duplicates the level list (once in the intro, once in the bulleted list, once echoing schema), and the repeated "Tin level:" phrasing suggests broken or malformed structure that wastes space. The critical behavioral fallback note is buried at the end.

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?

For a relatively simple 3-parameter, no-output-schema logging tool, this description is thorough: it addresses selection guidance, edge cases (alias, invalid values), and implicit preconditions (an active session). The only gaps are the awkwardly truncated "Tin level" sections and no explicit statement about what happens when targeting a non-existent or inactive session ID.

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?

The schema already covers all 3 parameters at 100% coverage, so this is a baseline-3 case. The description does add genuine semantic value for the "level" parameter (alias handling and invalid-value fallback that the enum alone can't express), but the id and message semantics are fully captured by the schema with no additional depth from the description.

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 clear verb+resource pairing ("Log a message to an active agent session") and elaborates with the concrete purposes: "record progress, decisions, or issues during a work session." While it doesn't explicitly name sibling tools, the focus on an existing, active session cleanly distinguishes it from creation and completion siblings in the family.

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 gives solid level-selection guidance, urging specific levels like "warning" or "error" for review verdicts and telling the agent which level to lead with. However, it provides no when-not-to-use guidance, no explicit alternatives, and the garbled "Tin level" passages read as truncated artifacts that muddy the otherwise clear advice.

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