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

Adds substantial behavior beyond the annotations: the call is asynchronous ('Accepted immediately, not done'), it instructs the agent to poll get_project until it leaves the analyzing state, then call get_config, and it discloses a cost ('uses one of the account's fresh analyses for the month'). The annotation set (non-readOnly, non-idempotent, non-destructive) does not carry any of this asynchronous or quota information.

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?

Front-loaded with the action, then usage, then the asynchronous follow-up, which is a sensible ordering. Three sentences with little waste, though the closing clause ('while editing the file yourself is free and you know what changed') is conversational and slightly over-long.

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 mutating, quota-consuming, asynchronous tool with no output schema, the description supplies the critical lifecycle (accepted → poll → fetch) and the cost. The remaining gap is that idempotency_key is undocumented, leaving the agent without guidance on retry behavior.

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, and it largely does not. project_id is only implied through 'the project's stack changed', and idempotency_key is never mentioned at all — notable given the annotations declare idempotentHint=false, which makes this parameter's semantics (retry safety) important and undocumented.

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 ('Re-run the analysis') and its object (the archive's fline.json, which it overwrites), making the exact effect clear. It is readily distinguishable from read-oriented siblings like get_config, check_config, and get_project.

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?

Gives an explicit triggering condition ('a configuration that has gone stale because the project's stack changed — a different package manager, a new lockfile') and an explicit alternative ('editing the file yourself is free and you know what changed'). This is a rare case of stating both when to use and when not to.

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