Show All Prime Change Orders

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

Annotations already cover read-only/idempotent safety, so the description's 'Read-only — it changes nothing in Procore' adds little. It does provide useful extra context: error payload details (401/403/404), the project_id default, and the 1/2-tier configuration constraint. However, the contradictory return-type statement ('Returns a single JSON object') introduces uncertainty about the actual response, undermining transparency.

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 structured but somewhat wordy at about 100 words. It includes redundant statements (read-only repeats annotations) and contradictory return-type descriptions that force the reader to reconcile conflicting information. The API/endpoint reference is useful but not tightly integrated. It earns no penalty for length alone but loses points for internal inconsistency.

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?

With no output schema, the description should clearly state what is returned, but it waffles between 'all Prime Change Orders' and 'a single JSON object.' It does explain failure modes and the project_id default, which is valuable. However, for a listing endpoint with 12 filter parameters, it omits pagination behavior and response structure, leaving the agent uncertain about how to handle results.

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%, giving baseline 3. The description adds meaningful semantics for the only required parameter: 'project_id defaults to the value set by procore_set_config when omitted.' This is information not present in the schema. No other parameters are discussed, but the schema already documents them thoroughly.

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 opens with a clear statement, 'Returns all Prime Change Orders for the specified Project,' which conveys the core function. However, it later contradicts this by claiming 'Returns a single JSON object describing the prime change order,' muddling whether this lists all records or fetches one. The usage phrase 'when you already know which prime change order you want' further blurs the line between this list-all tool and a singular show tool.

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?

Some usage context is given: the endpoint only supports 1 and 2 tier change order configurations, and project_id defaults to procore_set_config. Yet the primary 'when to use' guidance is misleading—saying 'use this when you already know which prime change order you want' is more appropriate for a single-record show tool, not a list-all endpoint. No alternatives are named, failing to distinguish from the sibling 'show_prime_change_order'.

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