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

Annotations already declare readOnlyHint=true, but the description adds substantial behavioral context: requires an API key, enforces ownership of the project, and deliberately returns the same generic not-found response for unknown/deleted/expired/not-owned project IDs. This goes far beyond the annotation to explain security and error-handling behavior.

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?

Four sentences, each earning its place: purpose, auth/ownership, exclusions/alternatives, and error behavior. Front-loaded with the core action, then essential caveats. No redundant wording or fluff.

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 simple two-parameter read tool with an output schema, the description fully covers purpose, constraints, alternatives, and error handling. The presence of an output schema means return-value details need not be in the description, so nothing important is missing.

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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics by tying project_id to ownership ('must belong to the calling key') and clarifying that version selects which version's summary/content hash is returned. This enhances the schema definitions, warranting a 4.

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?

Uses a specific verb ('Retrieve') and resource ('durable house project summary metadata'), listing exact fields returned (title, type, version, timestamps, content hash). It explicitly distinguishes from the full-spec retrieval tool by naming house_ref and project_versions, making its purpose unmistakable.

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?

Provides clear when-to-use context ('summary metadata') and explicit when-not-to-use guidance: 'Does NOT return the full house specification' with named alternatives (house_ref with palette_pdf, project_versions). Also states the ownership requirement, aiding the agent in deciding applicability.

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