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

Annotations already declare this is a non-read-only, idempotent, non-destructive, closed-world mutation, so the safety profile is covered. The description adds only the vague clause 'privacy-filtered project metadata' and says nothing about what the session record becomes after finishing, whether prior data is preserved, or the effect of the version conflict implied by expectedVersion.

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?

It is a single short sentence with no padding, which is structurally clean. However the wording is awkward ('Update hosted finish agent session') and front-loads nothing an agent needs, so brevity comes at the cost of usefulness rather than serving it.

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?

This is a complex mutation with 10 parameters, 6 required, a nested codeChanges object, no output schema, and no annotation coverage of outcome semantics. A one-line description that merely echoes the name leaves the agent without the information needed to invoke it correctly.

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 only 50%, yet the description explains none of the 10 parameters, including the required codeChanges array and its completion-declaration semantics, idempotencyKey, or expectedVersion. The only informal mapping is 'project metadata' to projectId/summary, which the schema already handles better.

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 'Update hosted finish agent session using privacy-filtered project metadata' largely restates the tool name rather than stating the action it performs (finalizing an agent session with a summary and code-change declaration). It never distinguishes itself from siblings like start_agent_session, finalize_agent_execution, or begin_agent_execution, so the agent learns nothing new about what this tool actually does.

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 when-to-use guidance, no statement of prerequisites (e.g. that it closes a session opened by start_agent_session), and no reference to alternatives such as finalize_agent_execution. The phrase 'privacy-filtered project metadata' hints at a constraint but never explains what it implies for the caller.

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