Symbol references

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

Annotations only supply readOnlyHint and openWorldHint; the description adds substantive context beyond them — the relative speed of each scope, that scope=workspace is implemented via content search (implying looser matching), the exact result shape, and a batch-safe guarantee, with no output schema to carry that.

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?

Labeled, front-loaded lines with zero filler — purpose first, then routing, then cost, output, and batching. Every line carries information an agent needs before invoking.

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 5-parameter read tool with thin schema coverage and no output schema, the description covers routing, cost, and the return shape thoroughly. The only gap is the unexplained distinction between limit and max_references, which leaves one invocation decision 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?

Schema coverage is only 20%, so the description must compensate; it does explain scope's two modes well, but limit and max_references are two integer caps with overlapping ranges that are never distinguished, leaving genuine ambiguity about which one to set.

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?

Opens with a specific verb and resource: 'Find every occurrence of a named symbol.' It immediately scopes the semantics with scope=file vs scope=workspace, which separates it from project_file_symbols (declarations) and project_search (arbitrary strings) named later.

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?

Explicit 'Use when' (before renaming/refactoring) and 'Avoid when' clauses that name both alternatives — project_file_symbols for declarations and project_search for arbitrary strings. This is the full when/when-not/alternative triad.

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