get_context

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

With no annotations, the description carries the full burden, and it does disclose what content comes back (handoff + memories) and the ordering expectation. However it says nothing about scope/empty state (what if no project or no handoff exists), whether the call is read-only, or rate/cost characteristics of an aggregate fetch.

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 short sentences, front-loaded with what it returns and immediately followed by the usage directive. Nothing extraneous.

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 2-param read tool with no output schema, the description covers intent and timing but omits scoping behavior (project default), return shape/size implications, and failure modes. Adequate to call, incomplete to call well.

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 50%; max_tokens is documented in the schema but 'project' is undocumented there. The description mentions neither parameter, so it fails to compensate for the gap — an agent cannot tell from the description whether omitting project yields a global or default-scoped context.

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?

Names the two things it returns (latest handoff + top memories), which is a specific resource pair rather than a tautology of 'get_context'. It implicitly contrasts with save_handoff/recall by being the read-and-prime entry point, but it never explicitly names a sibling.

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?

'Call first in every chat' gives an explicit, actionable trigger for when to use it. It stops short of naming alternatives (e.g., why not recall or list_projects first) or stating exclusions, so it is clear context without full routing guidance.

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