list_party_projects

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

Annotations already cover readOnlyHint=true and destructiveHint=false voices, so the description credits the safety profile. It adds genuine behavioral value by revealing the return shape ('same record shape as get_project, filtered to one party') and the performance rationale ('without enumerating all projects'). This exceeds the baseline but stops short of covering pagination or ordering behavior, which would make it fully transparent.

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?

Two sentences carry a precise purpose, a memory hook (the literal query 'what projects is X involved in?'), a return-shape note, and the analogue pointer. Every clause earns its place; the most critical information (purpose and unique behavior) is front-loaded.

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 filtered read-only list tool with pagination defaults in the schema and a reference to get_project's record shape, the description covers the key gaps: input semantics (embed), filtering behavior, and analogue routing. It does not spell out pagination behavior or maximum pages, but given the schema's explicit defaults (perPage max 100), the description is reasonably complete for a moderately complex tool.

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 only 25% (only embed has inline documentation). The description adds a concrete embed example ('tags,fields'), which is helpful, but it does not clarify the semantics of page/perPage defaults or the partyId requirement. The standard pagination parameters are left to schema defaults, so the description only marginally compensates for the low schema coverage.

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 uses a specific verb+resource ('List projects linked to a given party') and immediately distinguishes this tool from enumerating all projects. It also names a clear natural-language use case ('what projects is X involved in?') and identifies the analogue (list_party_opportunities), making its niche unmistakable relative to siblings.

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 explicitly states when to use it (to answer 'what projects is X involved in?' without enumerating all projects) and names the opportunity-side analogue (list_party_opportunities). However, it does not explicitly mention when NOT to use it, such as when the full unfiltered project list is needed, leaving list_projects/filter_projects open. This is clear guidance with a small gap.

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