ContextDrop

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

With no annotations, the description carries the full burden, yet it says nothing about side effects, auth requirements, or what the call returns. "Get" weakly implies a read, but there is no confirmation that this is non-destructive or whether it has any cost.

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?

A single front-loaded sentence with no filler. It is efficient, though the brevity reflects under-specification rather than tight editing.

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 zero-parameter tool with no output schema and no annotations, the description is the only source of information about the return value, and it does not say what the workspace or generated context actually contains. An agent cannot predict the shape or usefulness of the response.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 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?

States a verb ("Get") and a resource ("ContextDrop workspace and its generated project context"), so the basic action is identifiable. However, "generated project context" is undefined product jargon, and the description never contrasts this with the memory siblings (save/search/update_memory), leaving the agent to guess whether it overlaps with them.

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?

No when-to-use guidance, no prerequisites, and no mention of the sibling tools. An agent has no signal for choosing get_project_context over search_memory or ping.

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?

No annotations are provided, so the description carries the full disclosure burden, and it delivers only a label. It does not say whether a failed health check surfaces as an error or a status value, whether it is cheap/rate-limited, or whether it touches any state. Only the absence of parameters hints that it is a harmless read.

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?

A single front-loaded sentence with no filler or redundancy. Every word earns its place, and nothing relevant could be removed without losing meaning.

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 annotations and no output schema, the description is the only source of behavioral information, and it stops at the name of the check. For a trivial zero-param probe this is close to sufficient, but the agent still cannot tell what a success or failure looks like.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the empty schema is fully consistent with a no-argument liveness probe.

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 concrete function (health check) scoped to a named system (ContextDrop MCP server), which an agent can parse instantly. Sibling tools are all memory/context operations, so 'ping' is self-evidently distinct, though the description doesn't explicitly say so.

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 term 'health check' implies the usage context (verifying server availability before or instead of real work), but the description never states when to call it, when not to, or what to do on failure. Usage is inferable rather than specified.

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?

With no annotations, the description carries the full burden and does disclose key traits: deduplication behavior on title match, a user-confirmation requirement before overwriting, and handoff to update_memory. It leaves unstated what happens when no active project exists, whether the save is reversible, or how failures surface, so it stops short of full disclosure for a mutation tool.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds a distinct decision rule. There is mild redundancy ("do not create a duplicate" restates the identical-information case), but nothing is padding.

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?

The workflow for a 4-parameter mutation tool is well covered, but with zero schema descriptions and no output schema, the description should explain the parameters it never mentions, particularly confirm_existing. Adequate for the decision logic, incomplete for invocation.

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 0% across 4 parameters, so the description must compensate and largely does not. It hints that 'title' is the dedup key, but 'content', 'category', and especially 'confirm_existing' (a boolean defaulting to false that plausibly gates the confirmation flow described) are never explained.

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 ("Save a new memory") plus the scope ("active ContextDrop project"), and explicitly names update_memory as the sibling used for the modify path. An agent can distinguish this from update_memory without opening either schema.

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 branching rules: skip if identical, create new if additive, ask the user and switch to update_memory if it conflicts with an existing decision. When-to-use, when-not-to-use, and the alternative are all stated rather than implied.

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?

No annotations exist, so the description carries the full behavioral burden. It implies read-only semantics through 'search' and discloses project scoping ('active project') plus a freshness consideration, which is useful. However, it says nothing about result ranking, result count, truncation, or whether search is keyword vs. semantic — relevant behavioral facts for an agent deciding how much to trust a hit.

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 capability sentence is front-loaded and each subsequent sentence adds an actionable instruction. The agent-directed advice about using results to avoid asking the user to repeat themselves is slightly redundant with the freshness note, but no sentence is pure filler.

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 simple one-parameter read tool this covers when and why to call it. With no output schema and no annotations, the description should describe what a result looks like (titles, snippets, timestamps, scores) so the agent can plan around it; the freshness hint gestures at timestamps but does not define the return shape.

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 0% — the single 'query' parameter has no description in the schema. The description partially compensates by saying matches happen 'by title or content', but leaves the matching mode (substring, keyword, natural-language) and any length/format expectations unspecified.

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 (search) and resource (active ContextDrop project memory), and narrows the matching surface to title or content. It is distinguishable from save_memory/update_memory, but does not clarify how it differs from the sibling get_project_context, which likely retrieves similar stored context.

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 a concrete trigger list — project-specific decisions, architecture, requirements, preferences, conventions — so the agent knows when to reach for it. It adds a caution about verifying stale memories. It stops short of a true exclusion clause or a named alternative (e.g. when to prefer get_project_context), which keeps it below 5.

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?

While no annotations exist, the description adds valuable behavioral context by specifying the target environment ('active ContextDrop project'). It confirms the 'mutation' nature of the tool, but provides no deep operational transparency like rate limits or success criteria.

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 definition is structured logically, flowing from the core function to decision constraints and workflow advice. It is efficient, though slightly longer than a simple imperative sentence.

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?

Given the lack of annotations and output schema, the description is highly complete. It provides the essential meta-knowledge regarding project scope and the required operational logic (confirm vs. auto-update).

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?

The context signals 0% schema description coverage. Despite listing the parameters in the schema, the description adds zero semantic meaning to `title`, `content`, or `category`. The agent must rely entirely on schema structure for parameter understanding.

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 clearly states the function: updating an existing memory. By focusing on 'update' and contrasting it with the other siblings (save_memory/search_memory), it precisely scopes its purpose.

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?

It provides excellent usage guidelines by defining the trigger ('user confirms that an existing memory should be changed'), outlining when *not* to use it ('Do not update a memory automatically'), and providing a required prerequisite workflow ('Use search_memory first').

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