get_decisions

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read/recall operation, but says nothing about scoping behavior when all six optional filters are omitted, result limits/ordering, or the cost of an unfiltered query.

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 single short sentence is front-loaded and free of waste, but for a tool with six undocumented and overlapping filters it is undersized rather than concise — there is room to add distinguishing detail without bloat.

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?

An output schema exists, so return-value documentation is not owed. Still, given six optional parameters with zero coverage and no annotations, the description leaves the invocation mechanics (which filters to combine, what an unfiltered call returns) entirely unresolved.

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?

All six parameters have 0% schema description coverage and the description mentions none of them. The schema exposes ambiguous pairs (repo vs repoId, projectId, tags vs relatedFiles vs query) with no explanation of how they interact or which to prefer, leaving the agent to guess.

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 states a specific verb and resource ('Recall past architecture decisions'), which is much clearer than a tautology. However, it never distinguishes this tool from its sibling log_decision, the obvious write-side counterpart, so an agent must infer the read/write split from names alone.

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?

'before acting' supplies a temporal trigger for use, which is more than nothing, but there is no statement of when not to use it, no mention of the log_decision sibling, and no guidance on which parameters are needed for which retrieval scenario.

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