analyze_project

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context beyond that: it operates over an in-memory model cached until data files change, formulas are parsed but never executed, and unreadable formulas are listed. This is meaningful extra detail.

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 front-loaded with the core purpose, but it then becomes a dense, semicolon-chained wall of text enumerating thirteen views in a single run-on sentence. While each view entry carries information, the lack of formatting or paragraph breaks makes it difficult to scan and violates conciseness and structure expectations.

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 complex tool with 15 parameters, 13 views, no output schema, and annotations already covering safety, the description is remarkably complete. It explains what each view does and even sketches output shapes (e.g., validate as {issueCount, bySeverity, issues[]}, ast as a logical tree with outline), leaving little that an agent would need to infer.

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%, so the per-parameter descriptions already carry the baseline. The description goes further by explaining how parameters combine with views—for example, `severity` filters the validate view, `expected` sets the dead-space band for metrics, and `thresholdSd` controls balance flagging. It adds contextual meaning beyond the schema's field-level notes.

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 opening sentence states a specific read-only analysis capability over the whole project model, and 'Nothing is written' distinguishes it from write-oriented siblings. However, it does not explicitly differentiate itself from other read-only query tools such as query_database, query_map, or get_project_context.

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 provides extensive guidance for the `view` parameter, effectively telling the agent which lens to use for each analysis task. It does not, however, say when to use analyze_project instead of sibling tools or when not to use it, leaving tool-level selection implied rather than explicit.

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