project_context

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

With no annotations, the description must carry behavioral disclosure, and it does: bounded result sizes (five summaries, eight Git hits), a precondition for deeper modes, and side-effect constraints ('never recursively loads a branch', 'never stores raw source automatically'). It could add more about return shape and error behavior, but the core safety and sequencing traits are explicit.

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?

Three dense sentences, all load-bearing, with the most important operational rule (summary-first) front-loaded. No repetition of schema or annotation content.

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 no-output-schema, no-annotation tool with eight parameters and high complexity, the description gives a usable high-level protocol but omits the return contract details and several advanced parameters. 'Mandatory next-choice contract' is named but not explained, and there is no output schema to fill that gap.

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 only 25%, so the description must compensate. It adds real meaning for depth and selected_node_ids (summary-first contract, up to three IDs) and bounds max_results, but it leaves evidence_witnesses, selected_witness_ids, and capability_config_hash entirely unexplained, which is a significant gap at this coverage level.

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 verb and object ('Load task context progressively') and explains what the tool returns: bounded summaries, Git hits, references, and a next-choice contract. It does not explicitly differentiate itself from sibling tools like project_boundary or knowledge_read, so it misses the full 5.

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 gives strong mode-ordering guidance: first call must be depth=summary, and deeper modes are only valid with up to three selected node IDs from that same result. It also states two absolute prohibitions (no recursive branch loading, no automatic raw-source storage). It stops short of naming alternative sibling tools for when project_context should be skipped.

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