get_context_budget

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

No annotations are provided, so the description carries the full transparency burden. It usefully notes that the token cost is approximate, and the operation is clearly inspect-like, but it could explicitly state that the file is not modified and no other side effects occur.

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 description is one focused sentence with no filler. It front-loads the core behavior and spends no words on irrelevant details.

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 tool with one parameter and no output schema, the description gives an agent enough to understand what it costs. The main miss is that the description does not clarify the output shape, only that it estimates token costs.

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 100%: the only parameter, 'file', is already documented as a path to a .hird source file. The description adds a little context about the file's contents, but most parameter meaning is already handled by 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?

The description states a specific verb (approximate token costs) and a specific resource (a file's types, effects, actors, supervisors, tools, and function signatures). This makes the tool's purpose clear and distinguishes it from sibling symbols-lookup and explain tools.

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 intended use is implied: the tool tells an agent how many tokens a context window would cost for the file's relevant definitions. However, there is no explicit guidance about when to choose this tool over get_context_for_symbol or other siblings.

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