cos_discovery

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

With no annotations, the description carries the burden but only discloses the immediate effect of the 'decision' parameter (triggers backtrack recommendation vs stores for later). It doesn't mention side effects, permissions, or what the returned data looks like, though an output schema exists. This is partial disclosure but provides some behavioral context.

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 concise (two sentences) and front-loads the core purpose. It avoids redundancy and is easy to scan. However, it's arguably underspecified, but that's a completeness issue, not a conciseness issue.

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 7 required parameters, zero annotations, and an output schema present, the description should provide more context on what constitutes a discovery and how the fields relate. It only addresses the decision field, leaving significant gaps in how to fill the other required parameters and what the tool returns.

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 0%, so the description must explain parameters. It only clarifies 'decision' with two example values ('backtrack_now', 'record_for_later'); the other 6 required parameters (kind, summary, impact_assessment, session_id, task_marker, persona_id) are completely undocumented in both description and schema. This leaves the agent guessing at their semantics.

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 clearly states a verb ('Capture') and resource ('mid-work discovery'), and it distinguishes two decision modes ('backtrack_now' vs 'record_for_later') that give the tool a specific identity compared to sibling tools like 'cos_observation_record' or 'cos_backtrack_log'. However, it doesn't precisely define what qualifies as a 'discovery', leaving some ambiguity.

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 implies usage context ('mid-work discovery') and describes two decision paths, but it doesn't explicitly state when to prefer this tool over siblings like 'cos_observation_record' or 'cos_backtrack_log'. The alternative 'record_for_later' vs 'backtrack_now' provides internal branching but no external guidance on when to use this tool.

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