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

Annotations already declare destructive=true, idempotent=true, readOnly=false, so the risk profile is known. The description adds genuinely new behavior: the tool loads the files' projects and references before rewriting, which explains cost and why batching matters — context the annotations cannot convey.

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 sentences, both front-loaded and dense with useful information: the first defines the operation, the second explains cost and the batching rule. No filler or restatement of the title.

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 destructive, mutating tool with no output schema and full schema coverage, the description covers purpose, cost behavior, and batching well. It does not say what is returned or how failures relate to partial rewrites, a minor gap given the schema already documents pre-write failure handling.

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 100%, so the schema already documents files, profile, and solutionPath thoroughly, including wildcard and separator behavior. The description only reinforces the batching aspect of 'files'; baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb (run cleanup) and resource (files), and enumerates exactly what it fixes: formatting, code style, unused usings, var usage, modifier order, braces. It is clearly a rewrite-in-place operation, distinct from a read-only sibling like resharper_inspect, though the sibling is not named.

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?

Gives explicit operational guidance: 'make one call per task with every modified file in it' tells the agent how to batch rather than call repeatedly. It lacks an explicit when-not/alternative statement (e.g., use inspect to preview), but the usage context is clear.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only that it returns warnings, errors and suggestions; it says nothing about runtime cost, the fact that analysis is solution-wide regardless of any file scoping, or that findings may be written to a pruned report file — all of which live only in the schema.

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?

One front-loaded sentence with a clear verb and scope, and no wasted words. It is appropriately sized given the schema carries the detail, though it stops short of any structure that would help an agent decide between sibling tools.

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 no output schema, the description does state what comes back (warnings, errors, suggestions), which is the key missing piece an agent would otherwise lack. The remaining complexity — detail levels, report file emission, solution resolution — is exhaustively documented in the parameter schema, so the definition is close to complete.

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 100% and each of the five parameters carries a detailed, non-obvious explanation in the schema itself. The description mentions no parameter names or semantics, so it adds nothing here, but the schema baseline of 3 applies.

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 names a specific verb+resource pair ("Run ReSharper code inspection") and clarifies the domain with parentheticals ("static analysis, lint") plus the target ("a C# solution"). It is clearly distinct from resharper_cleanup and resharper_reset_cache by implication, but never names or contrasts those siblings explicitly.

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?

Usage is implied by "over a C# solution" but there is no statement of when to prefer this over resharper_cleanup, nor any prerequisites (e.g. a solution must be locatable via solutionPath or JB_SOLUTION_PATH). The agent must infer the routing from the tool names alone.

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

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description goes further by quantifying the cost ('costs the next call a full cold analysis') and disclosing a non-obvious lifecycle behavior ('a deleted checkout's cache outlives it'), neither of which is derivable from the annotations or schema.

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?

Four sentences with no filler; the core purpose and the wrong-condition warning are front-loaded, and each sentence contributes a distinct fact. It is slightly dense and could be split for skimming, but nothing is redundant.

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 single-parameter cache-reset tool with no output schema, the description covers purpose, trigger condition, prerequisite, cost, and the edge case of a stale deleted checkout. An agent has everything needed to decide to call it and to supply the parameter correctly.

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 100% and already explains that solutionPath overrides JB_SOLUTION_PATH and working-directory discovery, so the baseline is 3. The description adds real meaning beyond the schema by explaining the reclaim use case ('pass its old solution path as solutionPath') for a checkout that no longer exists, raising it above baseline.

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?

States a specific verb and resource ('Delete this solution's ReSharper analysis cache') plus the consequence (next inspect or cleanup rebuilds from cold), which immediately separates it from the sibling inspect/cleanup tools. An agent can identify exactly what this operates on without inferring from the name.

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?

Gives the precise diagnostic condition for use ('inspect reporting compilation errors a successful build does not'), an explicit prerequisite and anti-case ('Build first, because on a checkout that was never built... the errors are real'), and a general exclusion ('not routine maintenance'). That is when-to-use, when-not-to-use, and a prerequisite all in one paragraph.

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